每日AI论文精选-2026-11-08

AI 论文精选速递

2026年11月08日 · 追踪前沿研究

1

VibeVoice Technical Report

Zhiliang Peng, Jianwei Yu 等13人

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

#next-token diffusion#continuous speech tokenizer#Encodec

https://arxiv.org/abs/2508.19205

https://hjfy.top/arxiv/2508.19205

https://github.com/microsoft/VibeVoice (56619)

2

TradingAgents: Multi-Agents LLM Financial Trading Framework

Yijia Xiao, Edward Sun 等4人

A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio.

#large language models#LLM#multi-agent systems

https://arxiv.org/abs/2412.20138

https://hjfy.top/arxiv/2412.20138

https://github.com/tauricresearch/tradingagents (121139)

3

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

Aaron J. Li, Weijia Xu 等11人

TokenEconomizer reduces recurring token costs of coding agents across sequential real-world tasks by pruning irrelevant tools, injecting micro-skills, and interrupting failure loops.

#coding agents#token efficiency#TokenEconomizer

https://arxiv.org/abs/2610.22732

https://hjfy.top/arxiv/2610.22732

https://github.com/microsoft/TokenEconomizer (4930)

4

Unlimited OCR Works

Youyang Yin, Huanhuan Liu 等17人

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

#end-to-end OCR#large language model#decoder

https://arxiv.org/abs/2606.23050

https://hjfy.top/arxiv/2606.23050

https://github.com/baidu/Unlimited-OCR (30832)

5

Persistent Recursive Worlds Enable Autonomous Software Evolution

Beichen Huang, Zhenyu Liang 等4人

Genesis organizes long-horizon software development around a persistent project rather than persistent agents, enabling multi-day compiler construction and numerical module reimplementation with low cost and high performance.

#DeepSeek V4 Flash#GLM 5.2

https://arxiv.org/abs/2608.10450

https://hjfy.top/arxiv/2608.10450

https://github.com/EMI-Group/genesis (552)

6

VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents

ZhengXian Wu, Qianhao Nie 等13人

VisSearch-Bench evaluates multimodal agents on visually intensive search tasks that require integrating visual context with external information, showing that even the best system fully solves only 26.47% of tasks.

#multimodal agents#visual context management#VisSearch-Bench

https://arxiv.org/abs/2611.04894

https://hjfy.top/arxiv/2611.04894

https://github.com/antins-labs/VisSearch-Bench-v1 (59)

7

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

Ruofeng Yang, Yongcan Li 等3人

ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers.

#LLMs#agent systems#model weights

https://arxiv.org/abs/2605.03042

https://hjfy.top/arxiv/2605.03042

https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep (18822)

8

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Prateek Chhikara, Dev Khant 等5人

Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.

#Mem0#memory-centric architecture#graph-based memory

https://arxiv.org/abs/2504.19413

https://hjfy.top/arxiv/2504.19413

https://github.com/mem0ai/mem0 (68554)

9

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Junbo Niu, Zheng Liu 等61人

MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy.

#document parsing#vision-language model#coarse-to-fine

https://arxiv.org/abs/2509.22186

https://hjfy.top/arxiv/2509.22186

https://github.com/opendatalab/MinerU (83273)

论文摘要由 AI 生成 · 仅供学习参考

生成时间: 2026-11-08 08:30

© 2026 AI 论文精选 · 共收录 9 篇