让多智能体通过隐式通信协作，提升复杂推理准确率
Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
- 将隐式通信作为可学习模块，联合优化信息编码与理解
- 在数学推理等任务上达26.7%（AIME24）和20.2%（GPQA-Diamond）准确率
- 适合需要高效协作的多智能体系统研究者使用
基于大语言模型的多智能体系统在复杂推理任务中表现优异，但现有工作多关注代理角色与编排，将智能体间通信视为固定接口。通过内部表示（如键值缓存）实现的隐式通信是文本协议的替代方案，但现有方法未联合优化通信与多智能体推理。为此，我们提出DiffMAS训练框架，将隐式通信视为多智能体系统的可学习组件。DiffMAS对多智能体隐式轨迹进行参数高效的监督训练，使智能体能共同学习如何在交互中编码和解释信息。在数学推理、科学问答、代码生成及常识推理基准上的实验表明，DiffMAS在推理准确率和解码稳定性方面均优于单智能体推理、基于文本的多智能体系统以及先前的隐式通信方法，在AIME24上达到26.7%，GPQA-Diamond上达到20.2%，并在多个推理基准上实现稳定提升。
原文摘要 · Abstract (English)
Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks.
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。