AI RESEARCH
GraphMind: Theorem Selection and Conclusion Generation Framework with Dynamic GNN for LLM Reasoning
arXiv CS.CL
•
ArXi:2511.19078v2 Announce Type: replace Large language models (LLMs) have nstrated impressive capabilities in natural language understanding and generation, including multi-step reasoning such as mathematical proving. However, existing approaches often lack an explicit and dynamic mechanism to structurally represent and evolve intermediate reasoning states, which limits their ability to perform context-aware theorem selection and iterative