Self-evolving AI agents for protein discovery and directed evolution
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 87 references that are in the map. First posted on arXiv 28 Mar 2026.
Builds on
7 of 87 references.
References · 7
- 2023GPT-4 Technical Reportcited by 18,396
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2024GPT-4o System Cardcited by 4,588
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
- 2025OpenAI GPT-5 System Cardcited by 989
- 2023Ankh: Optimized Protein Language Model Unlocks General-Purpose Modellingcited by 45
- 2025Ankh3: Multi-Task Pretraining with Sequence Denoising and Completion Enhances Protein Representationscited by 3
Built on by
Not cited yet.