DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
This addresses the need for more adaptive and interpretable coordination in multi-agent systems for tasks like code generation and mathematical reasoning, representing a novel method for a known bottleneck rather than a foundational breakthrough.
The paper tackles the problem of inefficient fixed communication patterns in multi-agent reasoning systems by introducing DyTopo, a dynamic routing framework that reconstructs communication graphs each round based on semantic matching, resulting in an average performance improvement of +6.2% over baselines across benchmarks.
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.