# Self-evolving AI agents for protein discovery and directed evolution

arXiv: https://arxiv.org/abs/2603.27303 · HTML: https://mlsanity.com/paper/2603.27303/

## 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 (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling](https://mlsanity.com/paper/2301.06568/) (2023)
- [Ankh3: Multi-Task Pretraining with Sequence Denoising and Completion Enhances Protein Representations](https://mlsanity.com/paper/2505.20052/) (2025)

## 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.