arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.07799cs.CLcs.AI
收藏

基于图扩散模型的多LLM代理通信拓扑动态生成

Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models

University of California Los Angeles(加州大学洛杉矶分校);University of Washington(华盛顿大学);Nanyang Technological University(南洋理工大学)

Eric Hanchen Jiang, Mengting Li, Guancheng Wan, Sophia Yin, Yuchen Wu, Xiao Liang, Xinfeng Li, Yizhou Sun, Wei Wang, Kai-Wei Chang, Ying Nian Wu

AI总结:

本文提出Guided Topology Diffusion框架,通过迭代构建过程生成适应任务需求的高效通信拓扑,优于现有方法。

摘要:

多代理系统效率依赖于其通信拓扑,但设计最优拓扑具有挑战性。本文引入Guided Topology Diffusion框架,通过条件离散图扩散模型生成任务自适应的通信拓扑,实现实时优化,显著提升LLM代理协作性能。

英文摘要:

The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial challenge, as it requires balancing competing objectives such as task performance, communication cost, and robustness. Existing frameworks often rely on static or hand-crafted topologies, which inherently fail to adapt to diverse task requirements, leading to either excessive token consumption for simple problems or performance bottlenecks for complex ones. To address this challenge, we introduce a novel generative framework called \textit{Guided Topology Diffusion (GTD)}. Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process. At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards (e.g., accuracy, utility, cost), enabling real-time, gradient-free optimization towards task-adaptive topologies. This iterative, guided synthesis process distinguishes GTD from single-step generative frameworks, enabling it to better navigate complex design trade-offs. We validated GTD across multiple benchmarks, and experiments show that this framework can generate highly task-adaptive, sparse, and efficient communication topologies, significantly outperforming existing methods in LLM agent collaboration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑