Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation

Researchers developed GYWI, a scientific idea generation system that combines author knowledge graphs with retrieval-augmented generation to help Large Language Models generate more controllable and traceable scientific ideas. The system significantly outperforms mainstream LLMs including GPT-4o, DeepSeek-V3, Qwen3-8B, and Gemini 2.5 in metrics like novelty, reliability, and relevance.

• →GYWI combines author knowledge graphs with RAG to provide controllable context for LLM-based scientific idea generation.
• →The system uses a hybrid retrieval mechanism combining RAG and GraphRAG for both depth and breadth knowledge retrieval.
• →A reinforcement learning-based prompt optimization strategy automatically guides LLMs to improve results.
• →Comprehensive evaluation across five dimensions shows GYWI outperforms GPT-4o, DeepSeek-V3, Qwen3-8B, and Gemini 2.5.
• →The research addresses key limitations in current LLM scientific idea generation including lack of academic context and inspiration traceability.