Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation
Keywords: Large Language Model, Multi-agent System, Collaboration Strategy, Automatic Scientific Discovery, Science of Science
TL;DR: We propose a multi-agent system that has the potential to improve scientific idea generation, suggesting promising avenues for exploring collaborative mechanisms in scientific research.
Abstract: The rapid advancement of scientific progress requires innovative tools that can accelerate discovery. While recent AI methods, particularly large language models (LLMs), have shown promise in tasks such as hypothesis generation and experimental design, they fall short in replicating the collaborative nature of real-world scientific practices, where diverse teams of experts work together to tackle complex problems. To address the limitation, we propose an LLM-based multi-agent system, i.e., Virtual Scientists (VirSci), designed to mimic the teamwork inherent in scientific research. VirSci organizes a team of agents to collaboratively generate, evaluate, and refine research ideas. Through comprehensive experiments, we demonstrate that this multi-agent approach outperforms the state-of-the-art method in producing novel and impactful scientific ideas, showing potential in aligning with key insights in the Science of Science field. Our findings suggest that integrating collaborative agents can lead to more innovative scientific outputs, offering a robust system for autonomous scientific discovery.
Primary Area: applications to robotics, autonomy, planning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1763
Loading