TL;DR
This paper introduces a multi-agent iterative search framework inspired by combinatorial innovation to enhance the diversity and novelty of research ideas generated by large language models, demonstrated in NLP tasks.
Contribution
It proposes a novel multi-agent iterative planning search strategy that improves idea diversity and quality over existing LLM-based methods.
Findings
Outperforms state-of-the-art baselines in diversity and novelty.
Generated ideas are comparable in quality to top-tier conference papers.
Framework effectively refines ideas through iterative multi-agent interactions.
Abstract
Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify novel directions. Although existing large language model (LLM)-based methods show promise in research idea generation, the ideas they produce are often repetitive and lack depth. To address this issue, this study proposes a multi-agent iterative planning search strategy inspired by com-binatorial innovation theory. The framework combines iterative knowledge search with an LLM-based multi-agent system to generate, evaluate, and re-fine research ideas through repeated interaction, with the goal of improving idea diversity and novelty. Experiments in the natural language processing domain show that the proposed method outperforms state-of-the-art…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
