Self-evolving AI agents for protein discovery and directed evolution

TL;DR

VenusFactory2 introduces an autonomous, self-evolving multi-agent framework that enhances protein discovery and optimization from natural language prompts, surpassing existing agents on relevant benchmarks.

Contribution

It presents a novel dynamic workflow synthesis approach with self-evolving agents for complex protein-related tasks, improving over static tools.

Findings

Outperforms well-known agents on VenusAgentEval benchmark

Autonomously organizes protein discovery from natural language prompts

Demonstrates effective self-evolving multi-agent infrastructure

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.