动态调整智能体通信拓扑，提升多轮推理准确性
DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
- 按每轮目标动态构建稀疏通信图，仅连接相关智能体
- 在多个任务上平均比最强基线高6.2分
- 生成可解释的协作路径图，适合研究推理过程
基于提示的大型语言模型构建的多智能体系统能改善多轮推理，但现有方法大多依赖固定、全程一致的通信模式，难以匹配迭代求解中阶段性的需求。我们提出DyTopo，一种由管理器引导的多智能体框架，每轮重构一个稀疏有向通信图。根据管理器的本轮目标，每个智能体输出轻量级自然语言查询（需求）和关键项（供给）描述；DyTopo对这些描述进行嵌入并执行语义匹配，仅沿生成边传递私密消息。在代码生成与数学推理基准测试中，使用四种LLM骨干网络，DyTopo始终优于最强基线（平均+6.2分）。除了精度提升，DyTopo还通过动态演化的通信图提供可解释的协作轨迹，支持对通信路径随轮次重组的定性分析。
原文摘要 · Abstract (English)
Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing pipelines rely on fixed, trajectory-wide communication patterns that are poorly matched to the stage-dependent needs of iterative problem solving. We introduce DyTopo, a manager-guided multi-agent framework that reconstructs a sparse directed communication graph at each round. Conditioned on the manager's round goal, each agent outputs lightweight natural-language query (need) and \key (offer) descriptors; DyTopo embeds these descriptors and performs semantic matching, routing private messages only along the induced edges. Across code generation and mathematical reasoning benchmarks and four LLM backbones, DyTopo consistently outperforms over the strongest baseline (avg. +6.2). Beyond accuracy, DyTopo yields an interpretable coordination trace via the evolving graphs, enabling qualitative inspection of how communication pathways reconfigure across rounds.
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。