# EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery

arXiv: https://arxiv.org/abs/2605.24018 · HTML: https://mlsanity.com/paper/2605.24018/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 21 of 21)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2505.13259/) (2025)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation](https://mlsanity.com/paper/2503.22708/) (2025)
- [SkCoder: A Sketch-based Approach for Automatic Code Generation](https://mlsanity.com/paper/2302.06144/) (2023)
- [Large Language Models for Scientific Synthesis, Inference and Explanation](https://mlsanity.com/paper/2310.07984/) (2023)
- [Accelerating Scientific Discovery with Generative Knowledge Extraction, Graph-Based Representation, and Multimodal Intelligent Graph Reasoning](https://mlsanity.com/paper/2403.11996/) (2024)
- [SciPIP: An LLM-based Scientific Paper Idea Proposer](https://mlsanity.com/paper/2410.23166/) (2024)
- [From Misuse to Mastery: Enhancing Code Generation with Knowledge-Driven AI Chaining](https://mlsanity.com/paper/2309.15606/) (2023)
- [ProBench: Benchmarking Large Language Models in Competitive Programming](https://mlsanity.com/paper/2502.20868/) (2025)
- [Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning](https://mlsanity.com/paper/2411.14497/) (2024)
- [ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents](https://mlsanity.com/paper/2407.03884/) (2024)
- [CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing](https://mlsanity.com/paper/2403.13583/) (2024)
- [Principles of scientific research team formation and evolution](https://mlsanity.com/paper/1403.2787/) (2014)
- [AutoSciLab: A Self-Driving Laboratory For Interpretable Scientific Discovery](https://mlsanity.com/paper/2412.12347/) (2024)
- [AutoOED: Automated Optimal Experiment Design Platform](https://mlsanity.com/paper/2104.05959/) (2021)

## Built on by (most cited first, 3 of 3)

- [Socratic agents for autonomous scientific discovery in high-dimensional physical systems](https://mlsanity.com/paper/2606.26722/) (2026)
- [Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery](https://mlsanity.com/paper/2609.35315/) (2026)
- [ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine](https://mlsanity.com/paper/2610.04339/) (2026)

## Abstract (arXiv)

Large language models (LLMs), have shown strong potential in scientific discovery, yet existing methods still face substantial challenges in the design of research workflows and multi-role collaboration mechanisms. To mitigate these issues, we propose EvoSci, a multi-agent scientific collaboration framework, which integrates bio-inspired evolution with knowledge graph modeling. To iteratively generate, evaluate, and refine research ideas, EvoSci incorporates multiple role-based agents, including mentor, researcher, and reviewer. By combining collaborative reasoning, shared memory, and evolutionary feedback, EvoSci significantly enhances the coherence and creativity of scientific exploration. Experiments on real-world research topics demonstrate that EvoSci significantly outperforms strong baselines in LLM-based structured peer-review and comparative ranking evaluations, achieving the highest overall peer-review score (ICLR 4.90) and top ranking (Top-10 = 54). These results suggest its superiority in both scientific idea generation and continuous discovery.