Self-evolving AI agents for protein discovery and directed evolution
It addresses the bottleneck of manual orchestration in protein scientific discovery for researchers, offering an autonomous alternative to static tool usage.
VenusFactory2 introduces a self-evolving multi-agent framework that autonomously synthesizes dynamic workflows for protein discovery and directed evolution, outperforming existing agents on the VenusAgentEval benchmark.
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.