EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
This work is significant for researchers and scientists seeking to generate more diverse and novel research ideas, addressing the limitations of current LLM-based approaches.
This paper tackles the problem of semantic convergence in LLM-assisted scientific idea generation, which limits diversity and novelty. The proposed EvoGens framework, inspired by evolutionary search, significantly improves novelty from 0.1 to 0.4 and diversity from 0.24 to 0.55, while maintaining idea quality.
Generating novel research ideas is fundamental to scientific progress. While Large Language Models (LLMs) show promise in assisting this process, existing approaches often exhibit semantic convergence, resulting in limited diversity and novelty. To address this, we introduce EvoGens, an evolution-inspired framework that recasts scientific idea generation as an evolutionary search over a population of ideas. EvoGens iteratively applies rank-based mutation with differentiated retrieval planning to incorporate external knowledge, and semantic-aware crossover to fuse complementary concepts for conceptual reorganization. A lightweight evaluation signal guides the selection process, encouraging sustained exploration while mitigating premature convergence. Extensive experiments demonstrate that EvoGens substantially enhances exploration capabilities compared to state-of-the-art baselines. Specifically, it improves the Novelty from 0.1 to 0.4 and the Diversity from 0.24 to 0.55, while maintaining comparable idea quality under the current automatic evaluation protocol. These findings suggest that evolutionary mechanisms can serve as a useful framework for exploration-oriented research ideation, especially for broadening the novelty and diversity of candidate ideas under a shared automatic evaluation setting.