English

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

Computation and Language 2026-01-28 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2601.19290,
  title  = {MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning},
  author = {Yimeng Wang and Jiaxing Zhao and Hongbin Xie and Hexing Ma and Yuzhen Lei and Shuangxue Liu and Xuan Song and Zichen Zhang and Haoran Zhang},
  journal= {arXiv preprint arXiv:2601.19290},
  year   = {2026}
}
R2 v1 2026-07-01T09:21:47.636Z