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

2026-05-20

AI Summary

Current large language models exhibit limitations in supporting systematic scientific workflows and multi-agent collaboration, hindering coherent and creative scientific discovery. This work proposes a biologically inspired multi-agent framework for scientific collaboration that deeply integrates evolutionary mechanisms with role-specialized agents for the first time. By orchestrating distinct roles—such as mentors, researchers, and reviewers—and leveraging knowledge graphs, shared memory, and evolutionary feedback, the framework iteratively generates, evaluates, and refines scientific ideas. The approach significantly enhances both the coherence and creativity of scientific exploration, substantially outperforming strong baselines on real-world tasks. In the ICLR structured peer review process, it achieved an average score of 4.90 and secured a top-10 placement in 54% of evaluations.

Abstract

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.

Problem

• scientific discovery
• research workflow
• multi-agent collaboration
• large language models
• role-based collaboration

Innovation

• multi-agent framework
• bio-inspired evolution
• knowledge graph
• scientific discovery
• collaborative reasoning