Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas
This addresses the challenge of improving creativity in LLM-generated scientific ideas for researchers and innovators, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of LLMs generating simplistic and repetitive research ideas by introducing an iterative planning and search approach that retrieves external knowledge to enhance novelty and diversity. The framework produces 3.4 times more unique novel ideas and generates at least 2.5 times more top-rated ideas compared to state-of-the-art methods.
Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions due to their limited ability in acquiring external knowledge for innovation. To address this problem, we introduce an enhanced planning and search methodology designed to boost the creative potential of LLM-based systems. Our approach involves an iterative process to purposely plan the retrieval of external knowledge, progressively enriching the idea generation with broader and deeper insights. Validation through automated and human assessments indicates that our framework substantially elevates the quality of generated ideas, particularly in novelty and diversity. The number of unique novel ideas produced by our framework is 3.4 times higher than without it. Moreover, our method outperforms the current state-of-the-art, generating at least 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation.