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.

翻译：基于提示的大型语言模型构建的多智能体系统能够提升多轮推理能力，然而现有流程大多依赖固定、全轨迹的通信模式，难以匹配迭代问题求解中不同阶段的动态需求。本文提出DyTopo——一种由管理器引导的多智能体框架，该框架在每轮推理中重构稀疏有向通信图。在管理器设定的轮次目标指导下，每个智能体生成轻量级自然语言查询（需求）与关键词（供给）描述符；DyTopo对这些描述符进行嵌入表示并执行语义匹配，仅沿诱导边路由私有消息。在代码生成与数学推理基准测试中，基于四种LLM骨干网络的实验表明，DyTopo始终优于最强基线（平均提升+6.2）。除准确性外，DyTopo通过动态演化的通信图生成可解释的协调轨迹，使得研究者能够定性观察通信路径在多轮推理中的重构过程。