Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations
- Published
- Source
- arXiv
- Paper number
- 1375
- Field
- Reasoning
- arXiv ID
- 2610.35598
Key points
- The authors proposed EoG, a framework that improves LLM graph reasoning using only the knowledge graph itself, without question annotations.
- A single LLM alternates between a Proposer that poses questions and a Solver that answers them through graph self-play.
- SVTS executes first-order logic queries on the graph to build training tasks with complete and correct answer sets.
- A boundary-aware curriculum rewards the Proposer by the Solver's score variance, keeping task difficulty on the Solver's capability boundary.
- With Qwen-2.5-7B, EoG exceeded the strongest baseline by 7.46 points in average Hit@1 and by 17.80 points on the industrial KG.
- The synthesized training questions barely overlapped with test questions, so the gains did not come from test-set leakage.
Paper links
External research summaries. These are not HDATF publications or measured product results.