Fork me on GitHub

智能体的L0~L5分级(Levels of agent automation,智能体自动化级别)

Table 4: Levels of agent automation

表4:智能体自动化级别

Level 等级

Description 描述

Key characteristics 关键特征

Examples 示例

Level 0: Manual (no automation) 0级:手动(无自动化)

No AI involvement; humans perform all actions无人工智能参与;所有操作均由人类执行

- No autonomy - 无自主性
- Tools are passive - 工具是被动的
- No perception, decision, or action loop- 无感知、决策或行动循环

Spreadsheets, command-line tools 电子表格、命令行工具

Level 1: Rule-based agents 一级:基于规则的智能体

Agents follow static logic (e.g., if-this-then-that) or rules; no context/environment perception or learning智能体遵循静态逻辑(例如,若此则彼)或规则;无上下文/环境感知或学习能力。

- Deterministic logic - 确定性逻辑
- No adaptation - 无适应性
- No memory use - 不使用记忆
- No goal-awareness - 无目标意识
- Human-in-the-loop for decision-making- 决策中的人在回路

Traditional RPA tools, a rules-based chatbot for simple Q&A, an interactive voice response (IVR) system that routes calls based on keywords传统的机器人流程自动化(RPA)工具、用于简单问答的基于规则的聊天机器人、一种基于关键词来转接电话的交互式语音应答(IVR)系统

Level 2: Reactive agents 二级:反应式智能体

Agents can adapt responses based on defined conditions/context; use a narrow set of predefined tools (e.g., APIs, databases) to accomplish tasks but within well-defined workflows initiated by humans智能体可以根据定义的条件/上下文调整回复;使用少量预定义的工具(如应用程序编程接口、数据库)来完成任务,但这些任务需在由人类发起的明确工作流程内进行。

- Can process structured/unstructured input- 能够处理结构化/非结构化输入
- Uses ML for input understanding; e.g., natural language processing (NLP)- 使用机器学习来理解输入;例如,自然语言处理(NLP)

- Executes decisions based on context and rigid workflows- 根据上下文和严格的工作流程执行决策
- Can execute decisions based on certain conditions (e.g., location)- 可以根据特定条件(例如位置)执行决策
- No long-term planning - 无长期规划
- Narrow domain-specific task autonomy- 特定领域的窄任务自主性

Intelligent RPA tools, chatbots that can answer common questions using a knowledge base, a location-based assistant (e.g., a local restaurant finder app)智能RPA工具、能够利用知识库回答常见问题的聊天机器人、基于位置的智能助手(例如,一款本地餐厅查找应用程序)

Level 3: Conditional autonomous agents3级:有条件的自主智能体

AI can pursue goals with intermediate planning under constraints人工智能可以在约束条件下通过中间规划来实现目标

May require human intervention for novel or complex situations对于新出现或复杂的情况,可能需要人工干预。  

- Task decomposition - 任务分解
- Reasoning and feedback loops - 推理与反馈循环
- Domain-bounded - 领域受限的
- Uses symbolic or learned policy for decisions- 使用符号化策略或习得策略进行决策

GenAI agents, and copilots 生成式人工智能智能体与副驾驶

Level 4: Strategic autonomous agents第4级:战略型自主智能体

Complex reasoning and task decomposition to proactively achieve complex goals with minimal or no human oversight复杂推理和任务分解,以便在最少或无需人工监督的情况下主动实现复杂目标

Highly adaptable and can function in dynamic environments适应性强,能够在动态环境中运行

 

- Use advanced model reasoning and capabilities (e.g., multi-modal)- 使用先进的模型推理和能力(例如,多模态) 
-Advanced tool use - 高级工具使用
- Proactive goal setting - 主动设定目标
- Long-horizon planning - 长期规划
- Can operate with partial observability and uncertainty- 可以在部分可观测和不确定的情况下运行
- Still domain bound - 仍然受领域限制

A domain-specific AI agent that can proactively plan and execute a workflow end-to-end (e.g., Salesforce Agentforce and Devin, a software engineering agent from Cognition AI)一种特定领域的人工智能智能体,它可以主动地端到端规划并执行工作流程(例如,Salesforce Agentforce以及来自Cognition AI的软件工程智能体Devin)

Multi-agent systems (e.g., AutoGPT) 多智能体系统(例如,AutoGPT)

Level 5: General autonomous agents—artificial general intelligence (AGI) agents第5级:通用自主智能体——通用人工智能(AGI)智能体

Agents can operate across multiple domains, autonomously set their own goals, and use adaptive strategies智能体可以跨多个领域运作,自主设定自己的目标,并使用适应性策略。

- Multi-domain - 多领域
- Meta-reasoning - 元推理
- Adaptive self-learning - 自适应自主学习
- Critical value alignment - 关键价值对齐

Hypothetical AGI agents, experimental假设的通用人工智能智能体,实验性的

Source: Omdia 来源:Omdia

posted @ 2025-07-08 15:53  stardsd  阅读(313)  评论(0)    收藏  举报