Self-evolving AI agents for protein discovery and directed evolution

Computer Science > Artificial Intelligence [Submitted on 28 Mar 2026] 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 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. Comments: 100 pages, 6 figures Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Quantitative Methods (q-bio.QM) Cite as: arXiv:2603.27303 [cs.AI]   (or arXiv:2603.27303v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.27303 Focus to learn more Submission history From: Yang Tan [view email] [v1] Sat, 28 Mar 2026 15:16:49 UTC (14,575 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CL q-bio q-bio.QM References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)