用强化学习提升大模型协作能力，让多个智能体更高效完成复杂任务。
Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance Optimization
- 将协作建模为去中心化部分可观测马尔可夫决策过程，训练时用全局信息优化策略。
- 在写作和编码任务中，处理速度提升3倍，代码测试通过率达74.6%。
- 适合需要多智能体协同的复杂工作流，如团队写作、联合编程等场景。
大语言模型在语言任务中表现良好，但在多智能体协作中缺乏协同意识，难以优化全局性能。本文提出一种强化学习增强的大模型智能体框架，将协作建模为去中心化部分可观测马尔可夫决策过程（Dec-POMDP），采用集中式训练、去中心化执行（CTDE）范式。引入群体相对策略优化（GRPO），在训练阶段利用全局信号联合优化各智能体策略，并设计简化联合奖励函数，平衡任务质量、执行速度与协作成本。在协作写作和编码基准上，该框架相较单智能体基线实现3倍的任务处理速度提升，写作结构/风格一致性达98.7%，代码测试通过率为74.6%。结果表明，该方法持续优于强大多智能体大模型基线，为复杂工作流中的可靠协作提供了可行路径。
原文摘要 · Abstract (English)
Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a reinforcement learning-augmented LLM agent framework that formulates cooperation as a decentralized partially observable Markov decision process (Dec-POMDP) and adopts centralized training with decentralized execution (CTDE). We introduce Group Relative Policy Optimization (GRPO) to jointly optimize agent policies with access to global signals during training, together with a simplified joint reward that balances task quality, speed, and coordination cost. On collaborative writing and coding benchmarks, our framework delivers a 3x increase in task processing speed over single-agent baselines, 98.7% structural/style consistency in writing, and a 74.6% test pass rate in coding. The approach consistently outperforms strong multi-agent LLM baselines and provides a practical path toward reliable collaboration in complex workflows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。