GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training

ArXi:2602.02518v2 Announce Type: replace-cross Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organized as heterogeneous graphs rather than plain text. Reasoning over such graphs requires models to follow schema-defined relations through precise function calls and to aggregate evidence across multiple rounds of interaction. We propose GraphDancer, a two-stage post-