Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents

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 ideation capabilities. Furthermore, we propose Idea Arena, an evaluation protocol that can comprehensively evaluate idea generation methods from different perspectives, aligning closely with the preferences of human researchers. Experimental results indicate that the CoI agent consistently outperforms other methods and shows comparable quality as humans in research idea generation. Moreover, our CoI agent is budget-friendly, with a minimum cost of \$0.50 to generate a candidate idea and its corresponding experimental design.