AIMAMay 20

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

arXiv:2605.2401873.8
Predicted impact top 44% in AI · last 90 daysOriginality Incremental advance
AI Analysis

For researchers using LLMs in scientific discovery, EvoSci provides a novel collaboration mechanism that improves idea coherence and creativity, but the gains are incremental over existing multi-agent approaches.

EvoSci introduces a bio-inspired multi-agent framework that uses role-based agents and knowledge graphs to iteratively generate and refine research ideas, achieving a top peer-review score of 4.90 (ICLR scale) and a Top-10 ranking of 54 on real-world topics.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes