Self-evolving AI agents for protein discovery and directed evolution

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tan, Yang, Zhang, Lingrong, Li, Mingchen, Yu, Yuanxi, Zhong, Bozitao, Zhou, Bingxin, Dong, Nanqing, Hong, Liang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912986684194816
author Tan, Yang
Zhang, Lingrong
Li, Mingchen
Yu, Yuanxi
Zhong, Bozitao
Zhou, Bingxin
Dong, Nanqing
Hong, Liang
author_facet Tan, Yang
Zhang, Lingrong
Li, Mingchen
Yu, Yuanxi
Zhong, Bozitao
Zhou, Bingxin
Dong, Nanqing
Hong, Liang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27303
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Self-evolving AI agents for protein discovery and directed evolution
Tan, Yang
Zhang, Lingrong
Li, Mingchen
Yu, Yuanxi
Zhong, Bozitao
Zhou, Bingxin
Dong, Nanqing
Hong, Liang
Artificial Intelligence
Computation and Language
Quantitative Methods
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.
title Self-evolving AI agents for protein discovery and directed evolution
topic Artificial Intelligence
Computation and Language
Quantitative Methods
url https://arxiv.org/abs/2603.27303