Compared with individual agents, large language model based multi-agent systems have shown great capabilities consistently across diverse tasks, including code generation, mathematical reasoning, and planning, etc. Despite their impressive performance, the effectiveness and robustness of these systems heavily rely on their communication topology, which is often fixed or generated in a single step. This restricts fine-grained structural exploration and flexible composition, resulting in excessive token utilization on simple tasks while limiting capability on complicated tasks. To mitigate this challenge, we introduce RADAR, a redundancy-aware and query-adaptive generative framework that actively reduce communication overhead. Motivated by recent progress in conditional discrete graph diffusion models, we formulate communication topology design as a step-by-step generation process, guided by the effective size of the graph. Comprehensive experiments on six benchmarks demonstrate that RADAR consistently outperforms recent baselines, achieving higher accuracy, lower token consumption, and greater robustness across diverse scenarios. Our code and data are available at https://github.com/cszhangzhen/RADAR.

翻译：相较于单个智能体，基于大语言模型的多智能体系统在代码生成、数学推理及规划等多样化任务中持续展现出卓越能力。尽管性能显著，其有效性与鲁棒性严重依赖通信拓扑结构——该结构常被固定或仅通过单步生成，这既限制了细粒度结构探索与灵活组合，又导致简单任务中令牌利用过度，同时制约了复杂任务的性能发挥。为应对这一挑战，我们提出RADAR——一种冗余感知且查询自适应的生成式框架，能够主动降低通信开销。受条件离散图扩散模型最新进展的启发，我们将通信拓扑设计建模为基于图有效规模的逐步生成过程。在六个基准测试上的综合实验表明，RADAR在多种场景下持续超越近期基线方法，实现了更高精度、更低令牌消耗及更强鲁棒性。相关代码与数据已开源至https://github.com/cszhangzhen/RADAR。