用自进化多智能体系统自动设计和优化蛋白质，仅需一句自然语言指令。
Self-evolving AI agents for protein discovery and directed evolution
- 构建自进化多智能体框架，动态合成工作流替代人工调度。
- 在VenusAgentEval基准上超越多个知名智能体，实现端到端蛋白发现。
- 适合生物医药研发人员、自动化实验设计者快速探索新蛋白功能。
蛋白质科学发现受限于信息与算法的手动协调，而通用智能体在复杂领域任务中表现不足。VenusFactory2 提出一个自主框架，通过自进化多智能体基础设施，将静态工具使用转变为动态工作流合成，以应对蛋白质相关需求。该框架在 VenusAgentEval 基准上优于一组知名智能体，并能仅凭单一自然语言提示，自主完成蛋白质的发现与优化流程。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。