多智能体讨论的上下文学习

摘要

近期，多智能体讨论（MAD）研究日益受到关注，该方法通过多个大语言模型实例进行结构化讨论以协同解决问题。然而我们发现，现有MAD方法易出现讨论不一致问题——由于各智能体上下文语境不匹配，模型难以形成连贯的解决方案。本文提出一种多智能体上下文学习方法（M2CL），通过为每个智能体训练能动态生成上下文指令的生成器，实现基于自动信息组织与精炼的逐轮语境生成。具体而言，受我们对上下文指令的理论启示，M2CL通过精心设计的自适应机制训练生成器，以控制上下文连贯性与输出差异度，使大语言模型能够规避对多数噪声的过早收敛，逐步达成正确共识。我们在学术推理、具身任务和移动控制等挑战性任务上评估M2CL，结果表明其性能显著超越现有方法20%-50%，同时具备良好的迁移性和计算效率。

English

Multi-Agent Discussion (MAD) has garnered increasing attention very recently, where multiple LLM instances collaboratively solve problems via structured discussion. However, we find that current MAD methods easily suffer from discussion inconsistency, LLMs fail to reach a coherent solution, due to the misalignment between their individual contexts.In this paper, we introduce a multi-LLM context learning method (M2CL) that learns a context generator for each agent, capable of dynamically generating context instructions per discussion round via automatic information organization and refinement. Specifically, inspired by our theoretical insights on the context instruction, M2CL train the generators to control context coherence and output discrepancies via a carefully crafted self-adaptive mechanism.It enables LLMs to avoid premature convergence on majority noise and progressively reach the correct consensus. We evaluate M2CL on challenging tasks, including academic reasoning, embodied tasks, and mobile control. The results show that the performance of M2CL significantly surpasses existing methods by 20%--50%, while enjoying favorable transferability and computational efficiency.

多智能体讨论的上下文学习

Context Learning for Multi-Agent Discussion

摘要

Support