Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents
Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, and Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao, Dang, Deli Zhao, Yu Rong, Tian Feng, Lidong Bing

TL;DR
This paper introduces a Chain-of-Ideas (CoI) agent leveraging LLMs to organize scientific literature in a chain structure, significantly improving research idea generation and evaluation efficiency, and achieving human-like quality at low cost.
Contribution
The paper proposes the CoI agent that mimics human research processes by organizing literature sequentially, and introduces Idea Arena for comprehensive evaluation of idea generation methods.
Findings
CoI agent outperforms existing methods in idea quality
CoI achieves comparable results to human researchers
Cost-effective at approximately $0.50 per idea
Abstract
Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay current with recent advances and identify meaningful research directions. Recent developments in large language models~(LLMs) suggest a promising avenue for automating the generation of novel research ideas. However, existing methods for idea generation either trivially prompt LLMs or directly expose LLMs to extensive literature without indicating useful information. Inspired by the research process of human researchers, we propose a Chain-of-Ideas~(CoI) agent, an LLM-based agent that organizes relevant literature in a chain structure to effectively mirror the progressive development in a research domain. This organization facilitates LLMs to capture the current advancements in research, thereby enhancing their…
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
Taxonomy
TopicsFinTech, Crowdfunding, Digital Finance · Scientific Computing and Data Management
