Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision

ArXi:2510.03323v2 Announce Type: replace Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving informative yet compact subgraphs that fit the LLM context. Existing retrievers often struggle, relying either on shallow embedding similarity or costly interactive policies that require excessive supervision. To address these challenges, we