Self-evolving AI agents for protein discovery and directed evolution

Yang Tan; Lingrong Zhang; Mingchen Li; Yuanxi Yu; Bozitao Zhong; Bingxin Zhou; Nanqing Dong; Liang Hong

Self-evolving AI agents for protein discovery and directed evolution

Artificial Intelligence 2026-03-31 v1 Computation and Language Quantitative Methods

Authors: Yang Tan , Lingrong Zhang , Mingchen Li , Yuanxi Yu , Bozitao Zhong , Bingxin Zhou , Nanqing Dong , Liang Hong

Abstract

Protein scientific discovery is bottlenecked by the manual orchestration of information and algorithms, while general agents are insufficient in complex domain projects. VenusFactory2 provides an autonomous framework that shifts from static tool usage to dynamic workflow synthesis via a self-evolving multi-agent infrastructure to address protein-related demands. It outperforms a set of well-known agents on the VenusAgentEval benchmark, and autonomously organizes the discovery and optimization of proteins from a single natural language prompt.

Keywords

autonomous agents multi-agent systems artificial intelligence

Cite

@article{arxiv.2603.27303,
  title  = {Self-evolving AI agents for protein discovery and directed evolution},
  author = {Yang Tan and Lingrong Zhang and Mingchen Li and Yuanxi Yu and Bozitao Zhong and Bingxin Zhou and Nanqing Dong and Liang Hong},
  journal= {arXiv preprint arXiv:2603.27303},
  year   = {2026}
}

Comments

100 pages, 6 figures

Self-evolving AI agents for protein discovery and directed evolution

Abstract

Keywords

Cite

Comments

Related papers