1
GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
两阶段课程后训练让LLM学会在图数据中探索和推理，创新训练方法带来更强推理能力。
arXiv:2602.02518v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, …