Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning

About

Large language models are increasingly deployed as multi-agent systems, where specialized roles communicate and collaborate through structured interactions to solve complex tasks that often exceed the capacity of a single agent. However, most existing systems still rely on a fixed role library and an execution-frozen interaction topology, a rigid design choice that frequently leads to task mismatch, prevents timely adaptation when new evidence emerges during reasoning, and further inflates inference cost. We introduce MetaGen, a training-free framework that adapts both the role space and the collaboration topology at inference time, without updating base model weights. MetaGen generates and rewrites query-conditioned role specifications to maintain a controllable dynamic role pool, then instantiates a constrained execution graph around a minimal backbone. During execution, it iteratively updates role prompts and adjusts structural decisions using lightweight feedback signals. Experiments on code generation and multi-step reasoning benchmarks show that MetaGen improves the accuracy and cost tradeoff over strong multi-agent baselines.

Yimeng Wang, Jiaxing Zhao, Hongbin Xie, Hexing Ma, Yuzhen Lei, Shuangxue Liu, Xuan Song, Zichen Zhang, Haoran Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Multi-agent system task solvingFinance
Accuracy41.9
21
Multi-agent system task solvingWorkBench
Accuracy49.2
21
Multi-agent system task solvingBrowsecomp
Accuracy51.3
21
Multi-agent system task solvingPlancraft
Accuracy47.9
21
Showing 4 of 4 rows

Other info

Follow for update