奖励引导自回归图生成实现高效多智能体通信拓扑设计
原标题：Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design
AI 摘要
RGA-Designer 是一种受 RLHF 启发的奖励引导自回归图生成方法，用于高效设计多智能体通信拓扑。它训练一个联合捕捉任务正确性和结构紧凑性的奖励模型，并以此微调预训练图生成器，在保持 ARG-Designer 任务准确率的同时，平均减少约 30% 的 token 消耗。该方法在六个基准上验证了有效性，代码已开源。
正文节选
Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design Abstract LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substantial token consumption. Recent work on automatic topology design, ARG-Designer, has reframed this problem as autoregressive graph generation. However, its training objective provides no explicit incentive for the model to generate sparse an