多代理-RAG-与-Hugging-Face-代码代理

多代理 RAG 与 Hugging Face 代码代理

原文：towardsdatascience.com/multi-agentic-rag-with-hugging-face-code-agents-005822122930/

大型语言模型已经显示出令人印象深刻的性能，并且随着每一代新模型的发布，它们仍在稳步改进。例如，聊天机器人和摘要等应用可以直接利用 LLM 的语言能力，因为它们只需要产生文本输出，这是它们的自然环境。大型语言模型还显示出理解和解决复杂任务的能力，但只要它们的解决方案仍然“停留在纸上”，即以纯文本形式，它们就需要外部用户代表它们采取行动并报告所提议行动的结果。代理系统通过让模型在环境中采取行动来解决此问题，通常是通过一组可以执行特定操作的工具。这样，LLM 可以通过与环境的交互，通过试错迭代地找到解决方案。

一个有趣的情况是，LLM 代理可以访问的工具本身就是代理：这是多代理系统的核心概念。多代理系统通过分配和委派任务给专业模型，并将它们的输出组合起来，像拼图一样解决问题。实现此类系统的一种常见方法是通过使用管理代理来协调和协调其他代理的工作流程。

代理系统，尤其是多代理系统，需要一个强大的语言模型作为骨干来正确执行，因为底层模型需要能够理解各种工具的目的和适用性，以及将原始问题分解成每个工具可以解决的子问题。因此，像 ChatGpt 或 Anthropic 的 Claude 这样的专有模型通常是代理系统的默认首选解决方案。幸运的是，开源语言模型在性能上持续取得巨大进步，以至于其中一些模型在某些情况下已经与专有模型相媲美。更有趣的是，规模适中的开源语言模型现在可以执行几年前难以想象的任务。

在这篇博客文章中，我将展示一个可以在消费级硬件上运行的“小型”LLM（大型语言模型）如何足够强大，能够驱动一个多代理系统并取得良好的效果。特别是，我将提供一个教程，说明您如何使用 Qwen2.5–7B-Instruct 创建一个多代理 RAG（阅读理解生成）系统。您可以在以下 GitHub 仓库中找到代码实现，以及一个说明性的 Colab 笔记本。

在深入系统架构的细节之前，我将回顾一些关于 LLM 代理的基本概念，这些概念将有助于更好地理解该框架。

ReAct

ReAct，在 ReAct: Synergizing Reasoning and Acting in Language Models 中提出，是构建 LLM 代理的一个流行框架。该方法的主要思想是将思维链提示的有效性纳入代理框架中。ReACT 由交织的推理和动作步骤组成：在大语言模型发出动作之前，会提示其提供一个思维序列。这样，模型可以创建动态推理轨迹来引导动作，并在与环境交互的过程中更新高级计划。这允许采用迭代和增量方法来解决给定任务。在实践中，ReAct 代理的工作流程由思维、动作和观察序列组成：模型在思维步骤中为一般计划和特定工具使用提供推理，然后在动作步骤中调用相关工具，最后在观察步骤中从环境中接收反馈。

下面是一个 ReACT 框架的示例。

ReACT、思维链和仅动作框架在问答任务中的比较。图片来自 ReAct: Synergizing Reasoning and Acting in Language Models。

代码代理

代码代理是一种特殊的 LLM 代理，它们使用可执行的 Python 代码与环境交互。它们基于论文 Executable Code Actions Elicit Better LLM Agents 中提出的 CodeAct 框架。CodeAct 与 ReAct 框架非常相似，不同之处在于每个动作都由任意可执行的代码组成，可以执行多个操作。为代理提供的手工制作的工具作为常规 Python 函数，代理可以在代码中调用这些函数。

与使用 JSON 或其他文本格式执行动作的传统代理相比，代码代理具有独特的优势：

它们可以利用现有的软件包，并结合手工制作的特定任务工具。
它们可以通过使用错误发生后返回的错误消息来自我调试生成的代码。
LLMs 对编写代码很熟悉，因为这在它们的预训练数据中普遍存在，使其成为编写它们动作的更自然格式。
代码自然允许存储中间结果和在单个动作中组合多个操作，而 JSON 或其他文本格式可能需要多个动作才能完成相同的工作。

因此，代码智能体可以提供比使用 JSON 或其他文本格式执行动作的智能体更好的性能和更快的执行速度。

代码智能体与使用 JSON 或文本作为动作的智能体之间的比较。图片来自 Executable Code Actions Elicit Better LLM Agents。

下面是原始论文中的一个具体示例，展示了代码智能体如何需要更少的动作来解决某些任务。

代码智能体与使用 JSON/文本动作格式的智能体相比。代码智能体可以在一个动作中执行多个操作。图片来自 Executable Code Actions Elicit Better LLM Agents。[RIVEDERE]

Hugging Face 的 transformers 库提供了构建智能体的有用模块，特别是代码智能体。Hugging Face 的 transformers 智能体框架将清晰性和模块化作为核心设计原则。这些原则在构建智能体系统时尤为重要：工作流程的复杂性使得控制架构的所有相互关联部分至关重要。这些设计选择使 Hugging Face 智能体成为构建定制和灵活智能体系统的优秀工具。当使用开源模型为智能体引擎提供动力时，Hugging Face 智能体框架的进一步优势在于允许轻松访问 Hugging Face 生态系统中的模型和实用工具。

Hugging Face 代码代理也解决了不安全的代码执行问题。事实上，让 LLM 无限制地生成代码可能会带来严重风险，因为它可能会执行不希望的行为。例如，一个幻觉可能会导致代理删除重要文件。为了减轻这种风险，Hugging Face 代码代理的实现采用了一种从底层开始的确保代码执行安全的方法：代码解释器只能执行明确授权的操作。这与通常自上而下的范式形成对比，后者从完全功能的 Python 解释器开始，然后禁止可能危险的操作。Hugging Face 的实现包括可以执行的安全、授权函数列表，并提供可以导入的安全模块列表。除非用户事先授权，否则任何其他内容都不能执行。您可以在他们的博客文章中了解更多关于 Hugging Face（代码）代理的信息：

代理式 RAG

检索增强生成（Retrieval Augmented Generation）已成为涉及大型语言模型（LLM）的信息检索任务的既定标准。它可以帮助保持 LLM 信息的更新，提供访问特定信息，并减少幻觉。它还可以通过返回模型生成答案所使用的来源来增强人类的可解释性和监督。通常的 RAG 工作流程，包括基于用户查询的语义相似性的检索过程以及使用检索信息的模型上下文增强，对于解决某些特定任务来说并不充分。不适合传统 RAG 的一些情况包括需要与信息源进行交互的任务、需要回答多个信息片段的查询，以及需要非平凡操作才能与源中实际包含的信息相连接的复杂查询。

对于传统的 RAG 系统来说，一个具体的挑战性例子是多跳问答（MHQA）。它涉及提取和组合多个信息片段，可能需要在对提取的信息和仍缺失的信息进行多次迭代推理过程。例如，如果模型被问及“桦木胶合板在乙醇中是否会浮起？”的问题，即使用于 RAG 的来源包含了这两种材料的密度信息，如果这两条信息没有直接关联，标准的 RAG 框架可能会失败。

为了增强 RAG 并避免上述缺点，一种流行的方法是使用代理系统。一个 LLM 代理可以将原始查询分解成一系列子查询，然后使用语义搜索作为工具来检索这些生成子查询的段落，随着收集到更多信息，它还会调整其计划。它可以自主决定是否已经收集到足够的信息来回答每个查询，或者是否应该继续搜索。通过扩展到多代理系统，代理 RAG 框架可以进一步增强，其中每个代理都有其定义的任务和职责。这允许，例如，将高级任务规划和与文档源交互分离。在下一节中，我将描述这样一个系统的实际实现。

基于代码代理的多代理 RAG

在本节中，我将讨论我用来实现基于代码代理的 Multi-Agentic RAG 系统的一般架构选择，该系统遵循 ReAct 框架。您可以在以下GitHub 仓库中找到剩余的详细代码实现。

多代理系统的目标是通过对维基百科上的必要信息进行搜索来回答问题。它由 3 个代理组成：

管理代理的职责是将任务分解成子任务，并使用它们的输出提供最终答案。
一个维基百科搜索代理，它可以在维基百科上找到相关页面，并合并从这些页面中提取的信息。
一个页面搜索代理，用于从提供的维基百科页面中检索和总结与给定查询相关的信息。

这三个代理以分层的方式组织：每个代理都可以将其在层次结构中立即下方的代理用作工具。特别是，管理代理可以调用维基百科搜索代理来查找有关查询的信息，而这个代理反过来可以使用页面搜索代理从维基百科页面中提取特定信息。

以下展示了架构图，其中指定了每个代理可以调用哪些手工制作的工具（包括包装其他代理的工具）。请注意，由于代码代理通过代码执行来行动，这些工具实际上并不是它们能使用的唯一工具，因为任何本地的 Python 操作和函数（只要得到授权）也可以使用。

展示代理和手工制作工具的架构图。图片由作者提供。

让我们深入了解架构中涉及的代理的工作细节。

管理代理

这是顶级代理，它接收用户的提问并负责返回答案。它可以通过提出查询并接收搜索的最终结果，将维基百科搜索代理作为一个工具来使用。它的目的是通过将用户问题分解成一系列子查询并将搜索结果组合起来，从维基百科收集必要的信息片段。

下面是用于此代理的系统提示，它基于 Hugging Face 默认提示模板构建。注意，提示中提供的示例遵循代理所使用的模型的聊天模板，在这种情况下，Qwen2.5–7B-Instruct。

You are an expert assistant who can find answer on the internet using code blobs and tools. To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
You will be given the task of answering a user question and you should answer it by retrieving the necessary information from Wikipedia. Use and trust only the information you retrieved, don't make up false facts.
To help you, you have been given access to a search agent you can use as a tool. You can use the search agent to find information on Wikipedia. Break down the task into smaller sub-tasks and use the search agent to find the necessary information for each sub-task.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need. These print outputs will be provided back to you by the user in the 'Observation:' field, which will be available as input for the next steps. Always print the output of tools, don't process it or try to extract information before inspecting it.
If an error rise while executing the code, it will be shown in the 'Observation:' field. In that case, fix the code and try again.

In the end you have to return a final answer using the `final_answer` tool.

Here are a few notional examples:
---
<|im_start|>user
Task: When was the capital of Italy founded?<|im_end|>
<|im_start|>assistant
Thought: Let's break up the task: I first need to find the capital of Italy and then look at its foundation date. I will use the tool `wikipedia_search_agent` to get the capital of Italy. Code:
```py

result = wikipedia_search_agent("Italy capital")

print("意大利的首都是：", result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Capital of Italy:According to the information extracted from the Wikipedia page 'Rome', the capital of Italy is Rome.<|im_end|>
<|im_start|>assistant
Thought: Now that I know that the capital of Italy is Rome, I can use the `wikipedia_search_agent` tool to look for its foundation date.
Code:
```py

result = wikipedia_search_agent("Rome foundation date")

print("罗马的建立：", result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 1] -> Observation:
Rome foundation: According to the information from the Wikipedia page 'Natale di Roma', the traditional foundation date of Rome is April 21, 753 BC.<|im_end|>
<|im_start|>assistant
Thought: Now that I have retrieved the relevant information, I can use the `final_answer` tool to return the answer.
Code:
```py

final_answer("根据传说，罗马成立于公元前 753 年 4 月 21 日，但考古证据表明其发展可以追溯到青铜时代。")

```py<end_action><|im_end|>
---
<|im_start|>user
Task: "What's the difference in population between Shanghai and New York?"<|im_end|>
<|im_start|>assistant
Thought: I need to get the populations for both cities and compare them: I will use the tool `search_agent` to get the population of both cities.
Code:
```py

population_guangzhou_info = wikipedia_search_agent("New York City population")

population_shanghai_info = wikipedia_search_agent("Shanghai population")

print("广州的人口：", population_guangzhou)

print("上海的人口：", population_shanghai)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Population Guangzhou: The population of New York City is approximately 8,258,035 as of 2023.
Population Shanghai: According to the information extracted from the Wikipedia page 'Shanghai', the population of the city proper is around 24.87 million inhabitants in 2023.<|im_end|>
<|im_start|>assistant
Thought: Now I know both the population of Shanghai (24.87 million) and of New York City (8.25 million), I will calculate the difference and return the result.
Code:
```py

population_difference = 24.87*1e6 - 8.25*1e6

answer=f"上海和纽约之间的人口差异为 {population_difference} 人。"

final_answer(answer)

```py<end_action><|im_end|>
---

On top of performing computations in the Python code snippets that you create, you have access to those tools (and no other tool):

<<tool_descriptions>>

<<managed_agents_descriptions>>

You can use imports in your code, but exclusively from the following list of modules: <<authorized_imports>>.  Do not try to import other modules or else you will get an error.
Now start and solve the task!

维基百科搜索代理

此代理向管理代理报告，它从管理代理那里接收查询，并负责返回从维基百科检索到的信息。它可以访问两个工具：

一个维基百科搜索工具，使用来自wikipedia 包的内置搜索功能。它接收一个查询作为输入，并返回一系列维基百科页面及其摘要。
一个页面搜索代理，用于从特定维基百科页面检索查询信息。

此代理收集回答查询所需的信息，将其进一步分解为子查询，并在需要时结合多个页面的信息。这是通过使用维基百科包的搜索工具来识别可能包含回答查询所需信息的页面来实现的：代理可以使用报告的页面摘要或调用页面搜索代理从特定页面提取更多信息。收集到足够的数据后，它将答案返回给管理代理。

系统提示是对 Hugging Face 默认提示的轻微修改，并跟随模型的聊天模板提供一些特定示例。

You are an expert assistant that retrieves information from Wikipedia using code blobs and tools. To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
You will be given a general query, your task will be of retrieving and summarising information that is relevant to the query from multiple passages retrieved from the given Wikipedia page. Use and trust only the information you retrieved, don't make up false facts. Try to summarize the information in a few sentences.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need. These print outputs will be provided back to you by the user in the 'Observation:' field, which will be available as input for the next steps. Always print the output of tools, don't process it or try to extract information before inspecting it.
If an error rise while executing the code, it will be shown in the 'Observation:' field. In that case, fix the code and try again.

In the end you have to return a final answer using the `final_answer` tool.

Here are a few notional examples:
---
<|im_start|>user
Task: Retrieve information about the query:"What's the capital of France?" from the Wikipedia page "France".<|im_end|>
<|im_start|>assistant
Thought: I need to find the capital of France. I will use the tool `retrieve_passages` to get the capital of France from the Wikipedia page.
Code:
```py

result = retrieve_passages("France capital")

print("法国的首都是：", result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Retrieved passages for query "France capital":
Passage 0: ... population of nearly 68.4 million as of January 2024\. France is a semi-presidential republic with its capital in Paris, the ...
Passage 1: ... France, officially the French Republic, is a country located primarily in Western Europe. Its overseas regions and territories ...
Passage 2: ... The vast majority of France's territory and population is situated in Western Europe and is called Metropolitan France. It is ...
Passage 3: ... France is a highly urbanised country, with its largest cities (in terms of metropolitan area population in 2021) being Paris ...
Passage 4: ... === Government ===nFrance.fr – official French tourism site (in English)...<|im_end|>
<|im_start|>assistant
Thought: Now that I know that the capital of France is Paris, I can use the `final_answer` tool to return the answer.
Code:
```py

final_answer("法国的首都是巴黎。")

```py<end_action><|im_end|>
---
<|im_start|>user
Task: Retrieve information about the query:"Tallest mountain in the World" from the Wikipedia page "List of highest mountains on Earth"<|im_end|>
<|im_start|>assistant
Thought: I need to find the tallest mountain in the world. I will use the tool `retrieve_passages` to look for data on the Wikipedia page.
Code:
```py

result = retrieve_passages("highest mountain")

print(result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 1] -> Observation:
Retrieved passages for query "highest mountain":
Passage 0: ... above sea level) is the world's tallest mountain and volcano, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. ...
Passage 1: ... As of December 2018, the highest peaks on four of the mountains—Gangkhar Puensum, Labuche Kang III, Karjiang, and Tongshanjiabu, all located in Bhutan or China—have not been ascended. ...
Passage 2: ... The highest mountains above sea level are generally not the highest above the surrounding terrain. ...
Passage 3: ... The highest mountain outside of Asia is Aconcagua (6,961 m or 22,838 ft), the 189th highest in the world. ...
Passage 4: ... the southern summit of Peru's tallest mountain, Huascarán, is another contender. Both have elevations above sea level more than 2 km (1.2 mi) less than that of Everest....
<|im_end|>
<|im_start|>assistant
Thought: The results don't clearly specify a clear result for the world's tallest mountain, I will use the tool `web_results` with a different query.
Code:
```py

result = retrieve_passages("world's tallest mountain")

print(result)

```py<end_action><|im_end|>
<|im_start|>user
Passages retrieved from page List of highest mountains on Earth:
Passage 0: ... The highest mountain outside of Asia is Aconcagua (6,961 m or 22,838 ft), the 189th highest in the world....
Passage 1: ... above sea level) is the world's tallest mountain and volcano, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. ...
Passage 2: ... The bases of mountain islands are below sea level, and given this consideration Mauna Kea (4,207 m (13,802 ft) above sea level) is the world's tallest mountain and volcano, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. ...
Passage 3: ... the southern summit of Peru's tallest mountain, Huascarán, is another contender. Both have elevations above sea level more than 2 km (1.2 mi) less than that of Everest. ...
Passage 4: ... The highest mountains are also not generally the most voluminous. Mauna Loa (4,169 m or 13,678 ft) is the largest mountain on Earth in terms of base area (about 5,200 km2 or 2,000 sq mi) and volume (about 42,000 km3 or 10,000 cu mi)...<|im_end|>
<|im_start|>assistant
Thought: I have found that Mauna Kea is the world's tallest mountain rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. I can use the `final_answer` tool to return the relevant information.
Code:
```py

final_answer("莫纳克亚山是世界上海拔最高的山峰，从太平洋海底升起约 10,203 米（33,474 英尺）。")

```py<end_action><|im_end|>
___
On top of performing computations in the Python code snippets that you create, you have access to those tools (and no other tool):

<<tool_descriptions>>

<<managed_agents_descriptions>>

You can use imports in your code, but only from the following list of modules: <<authorized_imports>>. Do not try to import other modules or else you will get an error.
Now start and solve the task!

页面搜索代理

此代理向维基百科搜索代理报告，该代理为其提供查询和维基百科页面的标题，并负责从该页面检索相关信息以回答查询。本质上，这是一个单代理 RAG 系统。为了执行此任务，此代理生成自定义查询并使用语义搜索工具检索与它们更相似的段落。语义搜索工具遵循简单的实现，将页面内容分割成块并使用 LangChain 提供的 FAISS 向量数据库进行嵌入。

以下为系统提示，仍然基于 Hugging Face 默认提供的提示

You are an expert assistant that finds answers to questions by consulting Wikipedia, using code blobs and tools. To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
You will be given a general query, your task will be of finding an answer to the query using the information you retrieve from Wikipedia. Use and trust only the information you retrieved, don't make up false facts. Cite the page where you found the information.
You can search for pages and their summaries from Wikipedia using the `search_wikipedia` tool and look for specific passages from a page using the `search_info` tool. You should decide how to use these tools to find an appropriate answer:some queries can be answered by looking at one page summary, others can require looking at specific passages from multiple pages.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need. These print outputs will be provided back to you by the user in the 'Observation:' field, which will be available as input for the next steps. Always print the output of tools, don't process it or try to extract information before inspecting it.
If an error rise while executing the code, it will be shown in the 'Observation:' field. In that case, fix the code and try again.

In the end you have to return a final answer using the `final_answer` tool.

Here are a few notional examples:
---
<|im_start|>user
Task: When was the ancient philosopher Seneca born?<|im_end|>
<|im_start|>assistant
Thought: I will use the tool `search_wikipedia` to search for Seneca's birth on Wikipedia. I will specify I am looking for the philosopher for disambiguation.
Code:
```py

result = search_wikipedia("塞涅卡哲学家出生")

print("result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Pages found for query 'Seneca philosopher birth':
Page: Seneca the Younger
Summary: Lucius Annaeus Seneca the Younger ( SEN-ik-ə; c.4 BC – AD 65), usually known mononymously as Seneca, was a Stoic philosopher of Ancient Rome, a statesman, dramatist, and in one work, satirist, from the post-Augustan age of Latin literature.
Seneca was born in Colonia Patricia Corduba in Hispania, a
Page: Phaedra (Seneca)
Summary: Phaedra is a Roman tragedy written by philosopher and dramatist Lucius Annaeus Seneca before 54 A.D. Its 1,280 lines of verse tell the story of Phaedra, wife of King Theseus of Athens and her consuming lust for her stepson Hippolytus. Based on Greek mythology and the tragedy Hippolytus by Euripides,
Page: Seneca the Elder
Summary: Lucius Annaeus Seneca the Elder ( SEN-ik-ə; c.54 BC – c. AD 39), also known as Seneca the Rhetorician, was a Roman writer, born of a wealthy equestrian family of Corduba, Hispania. He wrote a collection of reminiscences about the Roman schools of rhetoric, six books of which are extant in a more or
Page: AD 1
Summary: AD 1 (I) or 1 CE was a common year starting on Saturday or Sunday, a common year starting on Saturday by the proleptic Julian calendar, and a common year starting on Monday by the proleptic Gregorian calendar. It is the epoch year for the Anno Domini (AD) Christian calendar era, and the 1st year of
Page: Seneca Falls Convention
Summary: The Seneca Falls Convention was the first women's rights convention. It advertised itself as "a convention to discuss the social, civil, and religious condition and rights of woman". Held in the Wesleyan Chapel of the town of Seneca Falls, New York, it spanned two days over July 19–20, 1848\.  Attrac
<|im_start|>assistant
Thought: From the summary of the page "", I can see that Seneca was born in . I can use the `final_answer` tool to return the answer.
Code:
```py

final_answer("根据维基百科页面'塞涅卡'的信息，塞涅卡出生于公元前 4 年。")

```py<end_action><|im_end|>
---
<|im_start|>user
Task: Who was Charlemagne predecessor?<|im_end|>
<|im_start|>assistant
Thought: I will use the tool `search_wikipedia` to search for Charlemagne reign duration.
Code:
```py

result = search_wikipedia("查理曼的继承者")

print(result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Pages found for query 'Charlemagne predecessor':
Page: Charlemagne
Summary: Charlemagne ( SHAR-lə-mayn; 2 April 748 – 28 January 814) was King of the Franks from 768, King of the Lombards from 774, and Emperor of what is now known as the Carolingian Empire from 800, holding these titles until his death in 814\. He united most of Western and Central Europe, and was the first
Page: Pope Leo III
Summary: Pope Leo III (Latin: Leo III; died 12 June 816) was bishop of Rome and ruler of the Papal States from 26 December 795 to his death. Protected by Charlemagne from the supporters of his predecessor, Adrian I, Leo subsequently strengthened Charlemagne's position by crowning him emperor. The coronation
Page: Throne of Charlemagne
Summary: The Throne of Charlemagne (German: Karlsthron or Aachener Königsthron, "Royal Throne of Aachen") is a throne erected in the 790s by Charlemagne, as one of the fittings of his palatine chapel in Aachen (today's Aachen Cathedral) and placed in the Octagon of the church. Until 1531, it served as the co
Page: Louis the Pious
Summary: Louis the Pious (Latin: Hludowicus Pius; French: Louis le Pieux; German: Ludwig der Fromme; 16 April 778 – 20 June 840), also called the Fair and the Debonaire, was King of the Franks and co-emperor with his father, Charlemagne, from 813\. He was also King of Aquitaine from 781\. As the only surviving
Page: Holy Roman Emperor
Summary: The Holy Roman Emperor, originally and officially the Emperor of the Romans (Latin: Imperator Romanorum; German: Kaiser der Römer) during the Middle Ages, and also known as the Romano-German Emperor since the early modern period (Latin: Imperator Germanorum; German: Römisch-deutscher Kaiser, lit. 'R
<|im_end|>
<|im_start|>assistant
Thought: The results don't contain explicit information about Charlemagne predecessor, I will search for more information on the page 'Charlemagne' using the 'search_info' tool.
Code:
```py

result = search_info("查理曼的继承者", "查理曼")

print(result)

```py<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 1] -> Observation:
Information retrieved from the page 'Charlemagne' for the query 'Charlemagne predecessor':
Charlemagne's predecessor was Pepin the Short.
<|im_end|>
<|im_start|>assistant
Thought: I have found that, according to the Wikipedia page 'Charlemagne', Pepin the Short was Charlemagne predecessor. I will return the results using the `final_answer` tool.
Code:
```py

final_answer("根据从维基百科页面'查理曼'提取的信息，他的继承者是矮子丕平。")

```py<end_action><|im_end|>
___
On top of performing computations in the Python code snippets that you create, you have access to those tools (and no other tool):

<<tool_descriptions>>

<<managed_agents_descriptions>>

You can use imports in your code, but only from the following list of modules: <<authorized_imports>>. Do not try to import other modules or else you will get an error.
Now start and solve the task!

实现选择

在本小节中，我将概述与使用 Hugging Face 代理架构的简单实现不同的主要点。这些是在获得一个合理有效的解决方案之前有限尝试和错误的成果。我没有进行广泛的测试和消融，因此它们可能不是最佳选择。

提示：如前几节所述，每个代理都有自己的专用系统提示，这与 Hugging Face 代码代理提供的默认提示不同。我观察到，可能由于使用的模型大小有限，通用的标准系统提示没有给出良好的结果。该模型似乎与反映其被要求执行的任务的系统提示效果最佳，包括定制的重要用例示例。由于我使用的是旨在改进指令遵循行为的聊天模型，因此提供的示例遵循模型的聊天模板，以尽可能接近运行期间遇到的格式。
总结历史： 长执行历史对执行速度和任务性能都有不利影响。后者可能是由于模型从长上下文中检索必要信息的有限能力。此外，极长的执行历史可能会超过引擎模型的上下文长度限制。为了减轻这些问题并加快执行速度，我选择不显示之前思维-行动-观察步骤的所有细节，而是只收集之前的观察。更具体地说，在每一步中，模型只接收以下聊天历史：系统消息、包含任务的第一个消息、其最后动作以及所有之前的观察历史。此外，只有在最后一步发生执行错误时，观察历史中才会出现执行错误，之前已经解决的错误会被丢弃。
工具与托管代理： Hugging Face 代理实现****对托管代理有原生支持，但将它们作为工具包装可以更好地控制提示并提供更流畅的实现。特别是，Hugging Face 实现为托管代理及其管理者添加了特定的提示。虽然我没有看到在解决给定任务的能力上有实质性差异，但我更喜欢第二种方法，因为它更灵活，对所展示的架构来说更流畅，并且可以更容易地控制代理的行为。这也帮助减少了提示长度，这对于加快计算速度是有用的。
限制页面搜索代理的最大尝试次数： 有时页面搜索代理会继续在一个不包含所需信息的页面上寻找信息。减少最大尝试次数可以减轻这个问题：达到该数字后，代理执行停止，工具返回代码执行的最后一个观察结果。
改变工具对用户消息的响应： 这更多是一个技术性、特定于实现的点。由于Qwen2.5–7B-Instruct聊天模板仅支持系统、用户和助手三种角色，因此观察结果以用户消息的形式返回。

示例

在本节中，我将收集一些使用所述架构生成的示例。我还会提供所有参与任务的代理的详细执行情况，以展示它们在某些实际案例中的交互。您可以使用说明性的Colab 笔记本探索更多示例。所有提取的段落均来自执行中指定的维基百科页面。

让我们从一个简单的例子开始，这个例子需要结合多个来源的信息和一些基本的算术理解。

任务：埃菲尔铁塔和帝国大厦建造之间相隔了多少年？

以下是管理代理执行日志。它可以正确地将任务分解为寻找两座建筑的建造时期并计算年份差异。

Agent:  Thought: First, I need to find out when the Eiffel Tower and the Empire State Building were constructed. I will use the `wikipedia_search_agent` tool to find this information.
Code:
```py

wikipedia_search_agent(query="Eiffel Tower construction year")

```py<end_action>
Observation:  Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Eiffel Tower', the construction of the Eiffel Tower took place from 1887 to 1889.
Agent:  Thought: Now I have the construction period of the Eiffel Tower. Next, I need to find the construction period of the Empire State Building. I will use the `wikipedia_search_agent` tool again.
Code:
```py

wikipedia_search_agent(query="Empire State Building construction year")

```py<end_action>
Observation:  Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Empire State Building', the construction of the Empire State Building started in 1930 and ended in 1931.
Agent:  Thought: Now I have the construction periods for both the Eiffel Tower and the Empire State Building. I can now calculate the number of years between their constructions. 
Code:
```py

construction_eiffel_tower_start = 1887

construction_eiffel_tower_end = 1889

construction_empire_state_building_start = 1930

construction_empire_state_building_end = 1931

years_passed = construction_empire_state_building_start - construction_eiffel_tower_end

answer = f"埃菲尔铁塔和帝国大厦之间建造年份的差距是 {years_passed} 年。"

final_answer(answer)

```py<end_action>
Observation:  Print outputs:
Last output from code snippet:
The number of years passed between the construction of the Eiffel Tower and the Empire State Building is 41 years.

现在我们可视化 Wikipedia 搜索代理的执行。它正确地搜索并报告了页面摘要中找到的建造时期，无需检查单个页面。值得注意的是，尽管被泛泛地询问“建造年份”，但它报告了整个建造时期，因为它不清楚年份是指建造工作的开始还是结束。

TASK:  Eiffel Tower construction year
AGENT:  Thought: I will use the `search_wikipedia` tool to find information about the Eiffel Tower construction year.
Code:
```py

search_wikipedia('Eiffel Tower construction year')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Pages found for query 'Eiffel Tower construction year':
Page: Eiffel Tower
Summary: The Eiffel Tower (  EYE-fəl; French: Tour Eiffel [tuʁ ɛfɛl] ) is a wrought-iron lattice tower on the Champ de Mars in Paris, France. It is named after the engineer Gustave Eiffel, whose company designed and built the tower from 1887 to 1889.
Locally nicknamed "La dame de fer" (French for "Iron Lady"), it was constructed as the centerpiece of the 1889 World's Fair, and to crown the centennial anniversary of the French Revolution. Although initially criticised by some of France's leading artists and intellectuals for its design, it has since become a global cultural icon of France and one of the most recognisable structures in the world. The tower received 5,889,000 visitors in 2022\. The Eiffel Tower is the most visited monument with an entrance fee in the world: 6.91 million people ascended it in 2015\. It was designated a monument historique in 1964, and was named part of a UNESCO World Heritage Site ("Paris, Banks of the Seine") in 1991.
The tower is 330 metres (1,083 ft) tall, about t
Page: Eiffel Tower (Paris, Texas)
Summary: Texas's Eiffel Tower is a landmark in the city of Paris, Texas. The tower was constructed in 1993\. It is a scale model of the Eiffel Tower in Paris, France; at 65 feet in height, it is roughly one-sixteenth of the height of the original. 

Page: Gustave Eiffel
Summary: Alexandre Gustave Eiffel (  EYE-fəl, French: [alɛksɑ̃dʁ ɡystav ɛfɛl]; né Bonickhausen dit Eiffel; 15 December 1832 – 27 December 1923) was a French civil engineer. A graduate of École Centrale des Arts et Manufactures, he made his name with various bridges for the French railway network, most famously the Garabit Viaduct. He is best known for the world-famous Eiffel Tower, designed by his company and built for the 1889 Universal Exposition in Paris, and his contribution to building the Statue of Liberty in New York. After his retirement from engineering, Eiffel focused on research into meteorology and aerodynamics, making significant contributions in both fields.
Page: Watkin's Tower
Summary: Watkin's Tower was a partially completed iron lattice tower in Wembley Park, London, England. Its construction was an ambitious project to create a 358-metre (1,175 ft)-high visitor attraction in Wembley Park to the north of the city, led by the railway entrepreneur Sir Edward Watkin. Marketed as the "Great Tower of London", it was designed to surpass the height of the Eiffel Tower in Paris, and it was part of Wembley Park's emergence as a recreational place. The tower was never completed and it was demolished in 1907\. The site of the tower is now occupied by the English national football ground, Wembley Stadium.
Page: Eiffel Tower (Paris, Tennessee)
Summary: The Eiffel Tower is a landmark in the city of Paris, Tennessee. It is a 1:20 scale replica of the original located in Paris, France.

AGENT:  Thought: From the summary of the page 'Eiffel Tower', I can see that the construction of the Eiffel Tower took place from 1887 to 1889\. I will use the `final_answer` tool to return the answer.
Code:
```py

final_answer("根据从 Wikipedia 页面'Eiffel Tower'提取的信息，埃菲尔铁塔的建造发生在 1887 年至 1889 年之间。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Eiffel Tower', the construction of the Eiffel Tower took place from 1887 to 1889.
------------------------------
TASK:  Empire State Building construction year
AGENT:  Thought: I will use the `search_wikipedia` tool to find information about the construction year of the Empire State Building.
Code:
```py

search_wikipedia('Empire State Building construction year')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Pages found for query 'Empire State Building construction year':
Page: Empire State Building
Summary: The Empire State Building is a 102-story Art Deco skyscraper in the Midtown South neighborhood of Manhattan in New York City. The building was designed by Shreve, Lamb &amp; Harmon and built from 1930 to 1931\. Its name is derived from "Empire State", the nickname of the state of New York. The building has a roof height of 1,250 feet (380 m) and stands a total of 1,454 feet (443.2 m) tall, including its antenna. The Empire State Building was the world's tallest building until the first tower of the World Trade Center was topped out in 1970; following the September 11 attacks in 2001, the Empire State Building was New York City's tallest building until it was surpassed in 2012 by One World Trade Center. As of 2024, the building is the seventh-tallest building in New York City, the ninth-tallest completed skyscraper in the United States, and the 57th-tallest completed skyscraper in the world.
The site of the Empire State Building, on the west side of Fifth Avenue between West 33rd and 34th St
Page: British Empire Building
Summary: The British Empire Building, also known by its address 620 Fifth Avenue, is a commercial building at Rockefeller Center in the Midtown Manhattan neighborhood of New York City. Completed in 1933, the six-story structure was designed in the Art Deco style by Raymond Hood, Rockefeller Center's lead architect. The British Empire Building, along with the nearly identical La Maison Francaise to the south and the high-rise International Building to the north, comprise a group of retail-and-office structures known as the International Complex. La Maison Francaise and the British Empire Building are separated by Channel Gardens, a planted pedestrian esplanade running west to the complex's Lower Plaza.
The facade is made of limestone, with a main entrance along Fifth Avenue and secondary entrances on 50th Street and Channel Gardens. The top of the British Empire Building contains setbacks, a rooftop garden, and a partial seventh-story penthouse. The building's entrances contain ornate decoration
Page: 2012 Empire State Building shooting
Summary: On August 24, 2012, a gunman shot and killed a former co-worker outside the Empire State Building in New York City. Following the initial shooting, the gunman, 58-year-old Jeffrey T. Johnson, was fatally shot by police officers after raising his weapon at them. Nine bystanders were wounded by stray bullets fired by the officers and ricocheting debris, but none suffered life-threatening injuries.
Page: Empire State Building in popular culture
Summary: The Empire State Building is a 102-story skyscraper on Fifth Avenue between West 33rd and 34th Streets in Midtown, Manhattan, New York City. It has a roof height of 1,250 feet (381 m), and with its antenna included, it stands a total of 1,454 feet (443.2 m) tall. The Empire State Building stood as the world's tallest building for nearly 40 years, from its completion in early 1931 until the topping out of the original World Trade Center's North Tower in late 1970\. It has been featured in numerous films, TV shows, songs, video games, books, photographs, and artwork.
Page: Empire State Plaza
Summary: The Governor Nelson A. Rockefeller Empire State Plaza (known commonly as the Empire State Plaza, and also as the South Mall) is a complex of several state government buildings in downtown Albany, New York.
The complex was built between 1965 and 1976 at an estimated total cost of $2 billion. It houses several departments of the New York State administration and is integrated with the New York State Capitol, completed in 1899, which houses the state legislature. Among the offices at the plaza are the Department of Health and the Biggs Laboratory of the Wadsworth Center. The Empire State Art Collection, a major public collection of 1960s and 1970s monumental abstract artworks, is on permanent display throughout the site. The New York State Office of General Services maintains the plaza. The Nelson A. Rockefeller Empire State Plaza Performing Arts Center Corporation is a New York state public-benefit corporation that was created in 1979 to manage the performing arts facility in the plaza.

AGENT:  Thought: From the summary of the page "Empire State Building", I can see that the building was designed and built from 1930 to 1931\. I will use the `final_answer` tool to return the answer.
Code:
```py

final_answer("根据从 Wikipedia 页面'Empire State Building'提取的信息，帝国大厦的建造始于 1930 年，结束于 1931 年。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Empire State Building', the construction of the Empire State Building started in 1930 and ended in 1931.

在所有信息都已包含在页面摘要中时，没有使用段落检索代理。

现在我们尝试一个更复杂的例子，询问桦木胶合板是否在酒精中漂浮。这个问题需要基本的物理理解和算术能力，并结合非平凡的检索任务。

任务：桦木胶合板是否在乙醇中漂浮？

首先可视化各个代理的日志。

管理代理日志

AGENT:  Thought: To determine if birch plywood floats in ethanol, we need to know the density of both birch plywood and ethanol. If the density of birch plywood is less than the density of ethanol, it will float. I will use the `wikipedia_search_agent` tool to find the densities of birch plywood and ethanol.
Code:
```py

birch_plywood_density_info = wikipedia_search_agent("density of birch plywood")

ethanol_density_info = wikipedia_search_agent("density of ethanol")

print(birch_plywood_density_info)

print(ethanol_density_info)

```py<end_action>
OBSERVATION:  Print outputs:
The density of birch plywood is approximately 680 kg/m³.
The density of ethanol at 20°C is approximately 0.7894 g/cm³.

AGENT:  Thought: Now that I have the densities, I can compare them. Birch plywood has a density of 680 kg/m³ and ethanol has a density of 0.7894 g/cm³. Since 1 g/cm³ is equal to 1000 kg/m³, the density of ethanol is 789.4 kg/m³. Since the density of birch plywood (680 kg/m³) is less than the density of ethanol (789.4 kg/m³), birch plywood will float in ethanol. I will now provide this conclusion using the `final_answer` function.
Code:
```py

final_answer("桦木胶合板会在乙醇中漂浮，因为它的密度（680 kg/m³）小于乙醇的密度（789.4 kg/m³）。")

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
Birch plywood will float in ethanol because its density (680 kg/m³) is less than the density of ethanol (789.4 kg/m³).

Wikipedia 搜索代理日志

TASK:  density of birch plywood
AGENT:  Thought: I will use the `search_wikipedia` tool to find information about the density of birch plywood. 
Code:
```py

search_wikipedia('birch plywood')

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
Pages found for query 'birch plywood':
Page: Plywood
Summary: Plywood is a composite material manufactured from thin layers, or "plies", of wood veneer that have been stacked and glued together. It is an engineered wood from the family of manufactured boards, which include plywood, medium-density fibreboard (MDF), oriented strand board (OSB), and particle board (or chipboard).
All plywoods bind resin and wood fibre sheets (cellulose cells are long, strong and thin) to form a composite material. The sheets of wood are stacked such that each layer has its grain set typically (see below) perpendicular to its adjacent layers. This alternation of the grain is called cross-graining and has several important benefits: it reduces the tendency of wood to split when nailed at the edges; it reduces thickness swelling and shrinkage, providing improved dimensional stability; and it makes the strength of the panel consistent across all directions.  There is usually an odd number of plies, so that the sheet is balanced, that is, the surface layers have their gr
Page: Birch
Summary: A birch is a thin-leaved deciduous hardwood tree of the genus Betula (), in the family Betulaceae, which also includes alders, hazels, and hornbeams. It is closely related to the beech-oak family Fagaceae. The genus Betula contains 30 to 60 known taxa of which 11 are on the IUCN 2011 Red List of Threatened Species. They are typically short-lived pioneer species and are widespread in the Northern Hemisphere, particularly in northern areas of temperate climates and in boreal climates. Birch wood is used for a wide range of purposes.
Page: Birch wood
Summary: Birch wood is a type of wood of the birch. Birch wood is pale yellow-brown wood having a close, straight grain and uniform texture that finishes to a smooth surface. Sometimes it is dyed to imitate mahogany. This type of wood is used for among others firewood, turnery, furniture, cabinetry, tools handles, hoops, plywood, flooring and shoe heels.
Page: Falco F8L
Summary: The Falco F8L is an Italian-designed lightweight 2-seater aerobatic aircraft.
Page: Crusader (speedboat)
Summary: Crusader was a jet-powered speed boat piloted by John Cobb.
The combination of an aerodynamically stable hull form and turbojet propulsion was proposed by Reid Railton, Cobb's adviser. A rocket-powered scale model was tested at Haslar. The full size design was by Peter du Cane and built by Vospers of Portsmouth. Technical assistance came from Saunders-Roe and Vickers-Supermarine. It cost £15,000 in 1949.
It was silver and scarlet in colour and 10 m long.  
The engine was a de Havilland Ghost Mk 48 centrifugal turbojet provided as a loan by the Ministry of Supply at the request of Major Frank Halford, the engine designer. The engine was rated at 5,000 lb thrust fed by two scoop inlets forward of the cockpit.
The hull was of trimaran form, a main hull with a planing step, and two smaller rear-mounted outriggers. Construction was of birch plywood frames and stringers. The hull was skinned in birch ply covered in doped fabric with metal skin reinforcement for planing surfaces. Aircraft-sty

AGENT:  Thought: The pages returned from the search did not directly mention the density of birch plywood. However, the page on Birch Wood mentions that birch wood is used for plywood. I will use the `search_info` tool to find more specific information about the density of birch plywood from the page 'Plywood'.
Code:
```py

search_info('density of birch plywood', 'Plywood')

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Plywood' for the query 'density of birch plywood':
The density of birch plywood is approximately 680 kg/m³.
AGENT:  Thought: I have found the density of birch plywood from the Wikipedia page 'Plywood'. The density is approximately 680 kg/m³.
Code:
```py

final_answer("桦木胶合板的密度大约为 680 kg/m³。")

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
The density of birch plywood is approximately 680 kg/m³.
------------------------------
TASK:  density of ethanol
AGENT:  Thought: I will use the `search_wikipedia` tool to find the density of ethanol from Wikipedia. 
Code:
```py

search_wikipedia('density of ethanol')

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
Pages found for query 'density of ethanol':
Page: Ethanol (data page)
Summary: This page provides supplementary chemical data on ethanol.

Page: Ethanol
Summary: Ethanol (also called ethyl alcohol, grain alcohol, drinking alcohol, or simply alcohol) is an organic compound with the chemical formula CH3CH2OH. It is an alcohol, with its formula also written as C2H5OH, C2H6O or EtOH, where Et stands for ethyl. Ethanol is a volatile, flammable, colorless liquid with a characteristic wine-like odor and pungent taste. In nature, grape-sugar breaks up by the action of fermentation into alcohol or carbonic acid, without anything being added. As a psychoactive depressant, it is the active ingredient in alcoholic beverages, and the second most consumed drug globally behind caffeine.
Ethanol is naturally produced by the fermentation process of sugars by yeasts or via petrochemical processes such as ethylene hydration. Historically it was used as a general anesthetic, and has modern medical applications as an antiseptic, disinfectant, solvent for some medications, and antidote for methanol poisoning and ethylene glycol poisoning. It is used as a chemical so
Page: Alcohol by volume
Summary: Alcohol by volume (abbreviated as alc/vol or ABV) is a standard measure of the volume of alcohol contained in a given volume of an alcoholic beverage, expressed as a volume percent. It is defined as the number of millilitres (mL) of pure ethanol present in 100 mL (3.5 imp fl oz; 3.4 US fl oz) of solution at 20 °C (68 °F). The number of millilitres of pure ethanol is the mass of the ethanol divided by its density at 20 °C (68 °F), which is 0.78945 g/mL (0.82353 oz/US fl oz; 0.79122 oz/imp fl oz; 0.45633 oz/cu in). The alc/vol standard is used worldwide. The International Organization of Legal Metrology has tables of density of water–ethanol mixtures at different concentrations and temperatures.
In some countries, e.g. France, alcohol by volume is often referred to as degrees Gay-Lussac (after the French chemist Joseph Louis Gay-Lussac), although there is a slight difference since the Gay-Lussac convention uses the International Standard Atmosphere value for temperature, 15 °C (59 °F).

Page: Alcohol fuel
Summary: Various alcohols are used as fuel for internal combustion engines.  The first four aliphatic alcohols (methanol, ethanol, propanol, and butanol)
are of interest as fuels because they can be synthesized chemically or biologically, and they have characteristics which allow them to be used in internal combustion engines. The general chemical formula for alcohol fuel is CnH2n+1OH.
Most methanol is produced from natural gas, although it can be produced from biomass using very similar chemical processes. Ethanol is commonly produced from biological material through fermentation processes. Biobutanol has the advantage in combustion engines in that its energy density is closer to gasoline than the simpler alcohols (while still retaining over 25% higher octane rating); however, biobutanol is currently more difficult to produce than ethanol or methanol. When obtained from biological materials and/or biological processes, they are known as bioalcohols (e.g. "bioethanol"). There is no chemical dif
Page: Cellulosic ethanol
Summary: Cellulosic ethanol is ethanol (ethyl alcohol) produced from cellulose (the stringy fiber of a plant) rather than from the plant's seeds or fruit. It can be produced from grasses, wood, algae, or other plants. It is generally discussed for use as a biofuel. The carbon dioxide that plants absorb as they grow offsets some of the carbon dioxide emitted when ethanol made from them is burned, so cellulosic ethanol fuel has the potential to have a lower carbon footprint than fossil fuels.
Interest in cellulosic ethanol is driven by its potential to replace ethanol made from corn or sugarcane. Since these plants are also used for food products, diverting them for ethanol production can cause food prices to rise; cellulose-based sources, on the other hand, generally do not compete with food, since the fibrous parts of plants are mostly inedible to humans. Another potential advantage is the high diversity and abundance of cellulose sources; grasses, trees and algae are found in almost every envi

AGENT:  Thought: The summary of the page 'Ethanol' mentions that ethanol is an alcohol with a characteristic wine-like odor and pungent taste. However, it does not provide the density of ethanol. I will use the `search_info` tool to find the density of ethanol from the 'Ethanol (data page)'.
Code:
```py

search_info('density of ethanol', 'Ethanol (data page)')

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ethanol (data page)' for the query 'density of ethanol':
The density of ethanol at 20°C is approximately 0.7894 g/cm³.
AGENT:  Thought: I have found the density of ethanol from the Wikipedia page 'Ethanol (data page)'. I will return the result using the `final_answer` tool.
Code:
```py

final_answer("20°C 时乙醇的密度大约为 0.7894 g/cm³。")

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
The density of ethanol at 20°C is approximately 0.7894 g/cm³.

页面搜索代理日志

TASK:  Retrieve information about the query:"density of birch plywood" from the Wikipedia page "Plywood".
AGENT:  Thought: I need to find the density of birch plywood. I will use the tool `retrieve_passages` to look for data on the Wikipedia page.
Code:
```py

result = retrieve_passages("桦木胶合板的密度")

打印结果

```py<end_action>
OBSERVATION:  Print outputs:
Retrieved passages for query "density of birch plywood":
Passage 0: ... . Shear stress, by contrast, is higher in the center of the panel, and at the outer fibres. Within Europe basic plywood can be divided into three main categories: birch plywood (density approx. 680 kg/m3), mixed plywood (density approx. 620 kg/m3) and conifer plywoods (density 460–520 kg/m3). ...
Passage 1: ... . Aircraft grade plywood is made from three or more plies of birch, as thin as 0.40 millimetres (1⁄64 in) thick in total, and is extremely strong and light. ...
Passage 2: ... Baltic Birch plywood is a product of an area around the Baltic Sea. Originally manufactured for European cabinet makers but now popular in the United States as well. It is very stable composed of an inner void-free core of cross-banded birch plys with an exterior grade adhesive. The face veneers are thicker than traditional cabinet grade ...
Passage 3: ... . As a result, thicker panels can span greater distances under the same loads. In bending, the maximum stress occurs in the outermost layers, one in tension, the other in compression. Bending stress decreases from the maximum at the face layers to nearly zero at the central layer. Shear stress, by contrast, is higher in the center of the panel, and at the outer fibres. Within Europe basic plywood can be divided into three main categories: birch plywood (density approx ...
Passage 4: ... Wind turbine blades
Insulation boxes for liquefied natural gas (LNG) carriers
Smooth surface and accurate thickness combined with the durability of the material makes birch plywood a favorable material for many special end uses e.g.:

High-end loud speakers
Die-cutting boards
Supporting structure for parquet
Playground equipment
Furniture
Signs and fences for demanding outdoor advertising
Musical instruments
Sports equipment...

AGENT:  Thought: From the passages, I can see that the density of birch plywood is approximately 680 kg/m³. I can use the `final_answer` tool to provide the answer.
Code:
```py

最终答案("桦木胶合板的密度约为 680 kg/m³。")

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
The density of birch plywood is approximately 680 kg/m³.
------------------------------
TASK:  Retrieve information about the query:"density of ethanol" from the Wikipedia page "Ethanol (data page)".
AGENT:  Thought: I need to find the density of ethanol. I will use the tool `retrieve_passages` to get the information from the Wikipedia page.
Code:
```py

result = retrieve_passages("乙醇的密度")

打印结果

```py<end_action>
OBSERVATION:  Print outputs:
Retrieved passages for query "density of ethanol":
Passage 0: ... == Density of ethanol at various temperatures ==
Data obtained from Lange 1967

These data correlate as ρ [g/cm3] = −8.461834×10−4 T [°C] + 0.8063372 with an R2 = 0.99999.

== Properties of aqueous ethanol solutions ==
Data obtained from Lange 1967

== Boiling points of aqueous solutions ==
Data obtained from CRC Handbook of Chemistry (Page 2117): 2391 

‡Azeotropic mixture

== Charts ==

== References == ...
Passage 1: ... This page provides supplementary chemical data on ethanol.

== Material Safety Data Sheet ==
External MSDS

== Structure and properties ==

== Thermodynamic properties ==

== Spectral data ==

== Vapor pressure of liquid ==

== Density of ethanol at various temperatures ==
Data obtained from Lange 1967

These data correlate as ρ [g/cm3] = −8.461834×10−4 T [°C] + 0.8063372 with an R2 = 0.99999.

== Properties of aqueous ethanol solutions ==
Data obtained from Lange 1967...

AGENT:  Thought: From the passages, I can see that the density of ethanol varies with temperature. I can use the provided linear equation to calculate the density at a specific temperature. I will use the `math` module to perform the calculation.
Code:
```py

# 从方程中提取系数

a = -8.461834e-4

b = 0.8063372

# 计算特定温度下的密度，以 20°C 为例

温度 = 20

密度 = a * 温度 + b

打印密度

```py<end_action>
OBSERVATION:  Print outputs:
0.789413532

AGENT:  Thought: The passage provides a linear equation to calculate the density of ethanol at different temperatures. I can now use this equation to provide the density of ethanol at a specific temperature. I will use the `final_answer` tool to return the relevant information.
Code:
```py

最终答案(f"乙醇在 20°C 时的密度约为{round(0.789413532, 4)} g/cm³。")

```py<end_action>
OBSERVATION:  Print outputs:
Last output from code snippet:
The density of ethanol at 20°C is approximately 0.7894 g/cm³.

模型正确地将密度差异识别为浮沉的原因，将任务分解为寻找两种物质的密度，并能够从检索到的数据中得出正确的结论，尽管它们使用不同的测量单位。

局限性

讨论的系统具有令人印象深刻的性能，尤其是考虑到使用的发动机模型规模有限，但当然，它也有自己的局限性。最大的一个似乎与发动机模型本身的力量有关：虽然它似乎能够理解并遵循复杂和长的指令，以及正确使用提供的工具，但有时它无法遵守简单的指南，并且倾向于重复无果的行动而不改变。这尤其明显当代理寻找的信息不存在（或无法使用语义搜索工具轻松提取）于提供的页面时。

另一个缺点，这是代理和甚至多代理系统固有的，是各种代理执行所需的计算时间。在某些简单的情况下，如果标准的 RAG 工作流程足以回答问题，这可能会产生不必要的计算开销。

最后，有多个代理相互交互可能会放大幻觉的风险，因为一个代理产生的幻觉可能会在执行链中传播，这使得跟踪也非常困难。

让我们可视化一个例子，其中系统虽然仍然提供正确的答案，但过度使用了工具调用（包括一些重复的操作），不必要地延长了执行时间。

任务：拜占庭帝国灭亡时，哪个朝代统治着中国？

这个任务需要较高的抽象能力，因为这两个事件并不相关，而且拜占庭帝国灭亡的确切年份可能不会在相应朝代的页面中报道。

管理代理执行仍然精简且准确，首先检索拜占庭帝国灭亡的日期，然后寻找那一年中国的朝代。然而，我们已经开始看到，虽然搜索结果仍然包含所需信息，但似乎有点奇怪。

Agent:  Thought: To answer this question, I need to find out when Constantinople fell and which Chinese dynasty was ruling at that time. I'll start by finding the fall date of Constantinople.
Code:
```py

搜索维基百科代理(query="拜占庭帝国灭亡")

```py<end_action>
Observation:  Print outputs:
Last output from code snippet:
The leader of the Ottoman Empire in 1453, during the fall of Constantinople, was Mehmed II, also known as Mehmed the Conqueror.
Agent:  Thought: From the previous search, we know that Constantinople fell in 1453, and it was conquered by Mehmed II. Now I need to find out which Chinese dynasty was ruling in 1453\. I will search for the Chinese dynasties around that time.
Code:
```py

搜索维基百科代理(query="1453 年中国朝代")

```py<end_action>
Observation:  Print outputs:
Last output from code snippet:
In 1453, the Ming dynasty was in full control of China. No specific events related to 1453 are mentioned in the information provided.
Agent:  Thought: Based on the information provided, the Ming dynasty was in full control of China in 1453\. Therefore, the dynasty ruling China when Constantinople fell would be the Ming dynasty.
Code:
```py

final_answer("1453 年君士坦丁堡陷落时统治中国的朝代是明朝。")

```py<end_action>
Observation:  Print outputs:
Last output from code snippet:
The dynasty ruling China when Constantinople fell in 1453 was the Ming dynasty.

因此，让我们检查相应的维基百科搜索代理任务及其执行情况。我们可以看到，可能由于广泛的任务"君士坦丁堡陷落"，代理在找到正确日期后还查看了一些其他具体信息。在检索有关中国朝代的信息时也发生了同样的事情，进一步的问题是某些工具调用被重复地以相同的方式调用。

TASK:  Fall of Constantinople
AGENT:  Thought: I will use the `search_wikipedia` tool to find information about the fall of Constantinople. This will likely provide me with a summary of the event and possibly links to related pages.
Code:
```py

search_wikipedia("君士坦丁堡陷落")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Pages found for query 'Fall of Constantinople':
Page: Fall of Constantinople
Summary: The fall of Constantinople, also known as the conquest of Constantinople, was the capture of the capital of the Byzantine Empire by the Ottoman Empire. The city was captured on 29 May 1453 as part of the culmination of a 55-day siege which had begun on 6 April.
The attacking Ottoman Army, which significantly outnumbered Constantinople's defenders, was commanded by the 21-year-old Sultan Mehmed II (later nicknamed "the Conqueror"), while the Byzantine army was led by Emperor Constantine XI Palaiologos. After conquering the city, Mehmed II made Constantinople the new Ottoman capital, replacing Adrianople.
The fall of Constantinople and of the Byzantine Empire was a watershed of the Late Middle Ages, marking the effective end of the Roman Empire, a state which began in roughly 27 BC and had lasted nearly 1500 years. For many modern historians, the fall of Constantinople marks the end of the medieval period and the beginning of the early modern period. The city's fall also stood as a turni
Page: Sack of Constantinople
Summary: The sack of Constantinople occurred in April 1204 and marked the culmination of the Fourth Crusade. Crusaders sacked and destroyed most of Constantinople, the capital of the Byzantine Empire. After the capture of the city, the Latin Empire (known to the Byzantines as the Frankokratia, or the Latin occupation) was established and Baldwin of Flanders crowned as Emperor Baldwin I of Constantinople in Hagia Sophia.
After the city's sacking, most of the Byzantine Empire's territories were divided up among the Crusaders. Byzantine aristocrats also established a number of small independent splinter states—one of them being the Empire of Nicaea, which would eventually recapture Constantinople in 1261 and proclaim the reinstatement of the Empire. However, the restored Empire never managed to reclaim all its former territory or attain its earlier economic strength, and it gradually succumbed to the rising Ottoman Empire over the following two centuries.
The Byzantine Empire was left poorer, smal
Page: Constantinople
Summary: Constantinople (see other names) became the capital of the Roman Empire during the reign of Constantine the Great in 330\. Following the collapse of the Western Roman Empire in the late 5th century, Constantinople remained the capital of the Eastern Roman Empire (also known as the Byzantine Empire; 330–1204 and 1261–1453), the Latin Empire (1204–1261), and the Ottoman Empire (1453–1922). Following the Turkish War of Independence, the Turkish capital then moved to Ankara. Officially renamed Istanbul in 1930, the city is today the largest city in Europe, straddling the Bosporus strait and lying in both Europe and Asia, and the financial center of Turkey.
In 324, following the reunification of the Eastern and Western Roman Empires, the ancient city of Byzantium was selected to serve as the new capital of the Roman Empire, and the city was renamed Nova Roma, or 'New Rome', by Emperor Constantine the Great. On 11 May 330, it was renamed Constantinople and dedicated to Constantine. Constantin
Page: Moscow, third Rome
Summary: Moscow, third Rome (Russian: Москва - третий Рим; Moskva, tretiĭ Rim) is a theological and political concept asserting Moscow as the successor to ancient Rome, with the Russian world carrying forward the legacy of the Roman Empire. The term "third Rome" refers to a historical topic of debate in European culture: the question of the successor city to the "first Rome" (Rome, within the Western Roman Empire) and the "second Rome" (Constantinople, within the Eastern Roman Empire).
Page: Byzantine Empire
Summary: The Byzantine Empire, also referred to as the Eastern Roman Empire, was the continuation of the Roman Empire centred in Constantinople during late antiquity and the Middle Ages. The eastern half of the Empire survived the conditions that caused the fall of the West in the 5th century AD, and continued to exist until the fall of Constantinople to the Ottoman Empire in 1453\. During most of its existence, the empire remained the most powerful economic, cultural, and military force in the Mediterranean world. The term "Byzantine Empire" was only coined following the empire's demise; its citizens referred to the polity as the "Roman Empire" and to themselves as "Romans". Due to the imperial seat's move from Rome to Byzantium, the adoption of state Christianity, and the predominance of Greek instead of Latin, modern historians continue to make a distinction between the earlier Roman Empire and the later Byzantine Empire.
During the earlier Pax Romana period, the western parts of the empire b

AGENT:  Thought: From the summary of the page "Fall of Constantinople", I can see that the event took place in 1453\. I will use the `search_info` tool to find more details about the event, specifically who was the leader of the Ottoman Empire at that time.
Code:
```py

search_info("1453 年奥斯曼帝国领导人", "君士坦丁堡陷落")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Fall of Constantinople' for the query 'leader of the Ottoman Empire in 1453':
The leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror.
AGENT:  Thought: I have found that the leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror. I will use the `final_answer` tool to provide the answer.
Code:
```py

final_answer("1453 年君士坦丁堡陷落时，奥斯曼帝国的领导人是穆罕默德二世，也被称为征服者穆罕默德。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
The leader of the Ottoman Empire in 1453, during the fall of Constantinople, was Mehmed II, also known as Mehmed the Conqueror.
------------------------------
TASK:  Chinese dynasties 1453
AGENT:  Thought: I will use the `search_wikipedia` tool to find information about Chinese dynasties around the year 1453\. I will provide a general query related to Chinese dynasties in that time period.
Code:
```py

search_wikipedia('1453 年 中国朝代')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Pages found for query 'Chinese dynasties 1453':
Page: Chinese Empire
Summary: Chinese Empire (or Empire of China) is a term referring to the realm ruled by the Emperor of China during the era known as Imperial China. It was coined by western scholars and used to describe the Ming and Qing dynasties (or imperial Chinese dynasties in general). Another term was "Celestial Empire", in reference to the status of the emperor as the Son of Heaven. In 221 BC, China was unified under an emperor for the first time, and various dynasties or empires founded by hereditary monarchs ruled China for a total of two millennia since then, including the Qin, Han, Jin, Sui, Tang, Song, Yuan, Ming, and Qing.

Page: Ming dynasty
Summary: The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662.
The Ming dynasty's founder, the Hongwu Emperor (r. 1368–1398), attempted to create a society of self-sufficient rural communities ordered in a rigid, immobile system that would guarantee and support a permanent class of soldiers for his dynasty: the empire's standing army exceeded one million troops and the navy's dockyards in Nanjing were the largest in the world. He also took great care breaking the power of the court eunuchs and unrelated magnates, enfeoff
Page: List of time periods
Summary: The categorisation of the past into discrete, quantified named blocks of time is called periodization. This is a list of such named time periods as defined in various fields of study.
These can be divided broadly into prehistorical periods and historical periods
(when written records began to be kept). 
In archaeology and anthropology, prehistory is subdivided into the three-age system, this list includes the use of the three-age system as well as a number of various designation used in reference to sub-ages within the traditional three.
The dates for each age can vary by region. On the geologic time scale, the Holocene epoch starts at the end of the last glacial period of the current ice age (c. 10,000 BC) and continues to the present. The beginning of the Mesolithic is usually considered to correspond to the beginning of the Holocene epoch.

Page: Celestial Empire
Summary: Celestial Empire (Chinese: 天朝; pinyin: Tiāncháo; lit. 'heavenly dynasty') is an old name used to refer to China or the Chinese Empire, from a literary and poetic translation of the Chinese term, one of many names for China. The name was used in reference to the status of the Emperor of China as the Son of Heaven in the Sinosphere.
Accordingly, in the 19th century, the name "Celestial" was used to refer to Chinese people. Both terms were widely used in the English-language popular mass media of the day, but fell into disuse later on. Its usage has become popular again in the present day (2015), particularly among Chinese Internet users. It is used to refer to the current Communist regime, to imply either disapproval for its political suppression and arrogance or national pride in the country's emergence as a superpower in the 21st century, depending on the context.
In modern times it has mostly fallen into disuse, but the name "Celestial Empire" still appears in various media such as ar
Page: List of dynasties
Summary: This is a list of monarchical dynasties and dynastic regimes organized by geographic region. Extant dynasties are rendered in bold and highlighted.

AGENT:  Thought: From the summaries, I can see that the Ming dynasty ruled from 1368 to 1644, which covers the year 1453\. I will use the `search_info` tool to find more detailed information about the Ming dynasty during the year 1453.
Code:
```py

search_info('1453', '明朝')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT:  Thought: Now that I know the Ming dynasty ruled during 1453, I can provide a more specific answer about the events that happened in China during that year. However, the information provided does not give us specific details about the events in 1453\. I will use the `search_info` tool to find more detailed information about the Ming dynasty during the year 1453.
Code:
```py

search_info('1453', '明朝')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT:  Thought: The information provided does not specifically mention the events of 1453\. However, we can infer that during the Ming dynasty, significant developments occurred. I will use the `search_info` tool to find more specific information about the events of 1453 in the Ming dynasty.
Code:
```py

search_info('1453', '明朝')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT:  Thought: The information provided indicates that the Ming dynasty was in full control of China during the year 1453\. However, there is no specific mention of events that happened in 1453\. I will use the `search_info` tool to find more specific information about the events of 1453 in the Ming dynasty.
Code:
```py

search_info('1453', '明朝')

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT:  Thought: The information provided does not specifically mention any events that occurred in 1453\. However, we know that the Ming dynasty was in full control of China during this time. I will use the `final_answer` tool to provide the answer based on the information we have.
Code:
```py

final_answer("1453 年，明朝完全控制了中国。提供的信息中没有提到与 1453 年相关的具体事件。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
In 1453, the Ming dynasty was in full control of China. No specific events related to 1453 are mentioned in the information provided.

深入研究页面搜索代理执行情况，我们发现这也重复了多个具有相同参数的工具调用。

TASK:  Retrieve information about the query:"leader of the Ottoman Empire in 1453" from the Wikipedia page "Fall of Constantinople".
AGENT:  Thought: I need to find out who was the leader of the Ottoman Empire in 1453\. I will use the `retrieve_passages` tool to search for this information on the Wikipedia page "Fall of Constantinople".
Code:
```py

result = retrieve_passages("1453 年奥斯曼帝国领导人")

print(result)

```py<end_action>
OBSERVATIONS:  Print outputs:
Retrieved passages for query "leader of the Ottoman Empire in 1453":
Passage 0: ... When Mehmed II succeeded his father in 1451, he was 19 years old. Many European courts assumed that the young Ottoman ruler would not seriously challenge Christian hegemony in the Balkans and the Aegean. In fact, Europe celebrated Mehmed coming to the throne and hoped his inexperience would lead the Ottomans astray. This calculation was boosted by Mehmed's friendly overtures to the European envoys at his new court. But Mehmed's mild words were not matched by his actions ...
Passage 1: ... The attacking Ottoman Army, which significantly outnumbered Constantinople's defenders, was commanded by the 21-year-old Sultan Mehmed II (later nicknamed "the Conqueror"), while the Byzantine army was led by Emperor Constantine XI Palaiologos. After conquering the city, Mehmed II made Constantinople the new Ottoman capital, replacing Adrianople. ...
Passage 2: ... . The oldest boy, renamed Murad, became a personal favourite of Mehmed and served as Beylerbey (Governor-General) of Rumeli (the Balkans). The younger son, renamed Mesih Pasha, became Admiral of the Ottoman fleet and Sancak Beg (Governor) of the province of Gallipoli. He eventually served twice as Grand Vizier under Mehmed's son, Bayezid II. ...
Passage 3: ... == External links ==

 Media related to Fall of Constantinople (1453) at Wikimedia Commons
The Siege of Constantinople As The Islamic World Sees it Archived 22 April 2021 at the Wayback Machine
World History Encyclopedia – 1453: The Fall of Constantinople
Constantinople Siege &amp; Fall, BBC Radio 4 discussion with Roger Crowley, Judith Herrin &amp; Colin Imber (In Our Time, 28 December 2006). ...
Passage 4: ... In the summer of 1452, when Rumeli Hisarı was completed and the threat of the Ottomans had become imminent, Constantine wrote to the Pope, promising to implement the union, which was declared valid by a half-hearted imperial court on 12 December 1452\. Although he was eager for an advantage, Pope Nicholas V did not have the influence the Byzantines thought he had over the Western kings and princes, some of whom were wary of increasing papal control...

AGENT:  Thought: From the passages, it seems that the leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror. I will use the `final_answer` tool to provide the answer.
Code:
```py

final_answer("1453 年奥斯曼帝国的领导人是穆罕默德二世，也被称为征服者穆罕默德。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
The leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror.
------------------------------
TASK:  Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT:  Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py

result = retrieve_passages("1453 明朝")

print(result)

```py<end_action>
OBSERVATIONS:  Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644\. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662\. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....

AGENT:  Thought: The passages do not directly mention the year 1453\. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py

final_answer("1453 年属于明朝时期，该朝代从 1368 年至 1644 年统治。在这段时间里，明朝完全控制了中国，并经历了诸如故宫的建设和长城的扩建等重大发展。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
------------------------------
TASK:  Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT:  Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py

result = retrieve_passages("1453 明朝")

print(result)

```py<end_action>
OBSERVATIONS:  Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644\. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662\. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....

AGENT:  Thought: The passages do not directly mention the year 1453\. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py

final_answer("1453 年属于明朝时期，该朝代从 1368 年至 1644 年统治。在这段时间里，明朝完全控制了中国，并经历了诸如故宫的建设和长城的扩建等重大发展。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
------------------------------
TASK:  Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT:  Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py

result = retrieve_passages("1453 明朝")

print(result)

```py<end_action>
OBSERVATIONS:  Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644\. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662\. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....

AGENT:  Thought: The passages do not directly mention the year 1453\. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py

final_answer("1453 年属于明朝时期，该朝代从 1368 年至 1644 年统治。在这段时间里，明朝完全控制了中国，并经历了诸如故宫的建设和长城的扩建等重大发展。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
------------------------------
TASK:  Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT:  Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py

result = retrieve_passages("1453 明朝")

print(result)

```py<end_action>
OBSERVATIONS:  Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644\. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662\. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....

AGENT:  Thought: The passages do not directly mention the year 1453\. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py

final_answer("1453 年属于明朝的时期，明朝从 1368 年至 1644 年统治中国。在这段时间里，明朝完全控制了中国，并经历了诸如故宫建设和长城扩张等重大发展。")

```py<end_action>
OBSERVATIONS:  Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644\. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.

结论

在这篇博客文章中，我解释了如何使用代码代理和“小型”开源 LLM（如Qwen2.5–7B-Instruct）创建多智能体 RAG 系统。我讨论了主要架构特征以及相对于 Hugging Face 代码代理实现的一些具体选择，这些选择是为了提高结果。完整的代码细节可在以下GitHub 仓库中找到。

尽管所描述的多智能体系统由运行在消费级硬件上的小型模型驱动，但它可以解决与复杂查询相关的多跳问答任务。特别是：

它可以将查询分解成可管理的子任务；
它可以识别包含必要信息的维基百科页面；
它可以结合来自多个页面的信息；
它可以在维基百科页面上搜索详细信息；
它可以确定是否需要更多信息，并尝试找到它；
它可以成功修复它产生的代码中的小错误并处理工具错误（如维基百科消歧错误）。

我还概述了该系统的某些局限性，例如计算时间增加、重复动作以及幻觉传播的潜在可能性。后者可以通过在系统中包含一个“校对员”代理来减轻，该代理会检查报告的信息是否与检索到的来源一致。

值得注意的是，由于智能体系统在其核心处采用标准的 RAG 方法，因此可以在此框架中实施所有用于提高后者效率和准确性的常用技术。

另一个可能的改进是使用技术来增加测试时间计算，给模型更多的“思考时间”，类似于 OpenAI o1/o3 模型。然而，需要注意的是，这种修改将进一步增加执行时间。

最后，由于多智能体系统由专门从事单个任务的代理组成，为每个代理使用不同的模型引擎可以提高性能。特别是，可以为系统中的每个任务微调不同的模型以获得进一步的性能提升。这对于小型模型尤其有益。值得一提的是，可以通过在一系列预定的任务上运行系统并保存系统产生正确答案时代理的输出，来收集微调数据，从而消除对昂贵的手动数据标注的需求。

我希望您觉得这个教程很有用，您可以在GitHub 仓库中找到完整的代码实现，并在Colab 笔记本中亲自尝试。

posted @ 2026-03-27 10:23 布客飞龙III 阅读(23) 评论(0) 收藏举报

刷新页面返回顶部

龙哥盟