{"slug": "hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-questions", "title": "HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questions", "summary": "A new framework called HyGRL, detailed in a preprint on arXiv, outperforms state-of-the-art baselines in answer accuracy and reasoning fidelity for multi-entity compositional questions while maintaining low token costs and near real-time inference. The method embeds unstructured text into structured knowledge graphs and uses imitation and reinforcement learning to refine reasoning. The code is available on GitHub.", "body_md": "arXiv:2607.19398v1 Announce Type: cross\nAbstract: Multi-entity compositional questions pose significant challenges to existing retrieval-augmented language models. Conventional methods fall into a dilemma: standard RAG lacks dynamic reasoning, traditional Graph-RAG is limited by structural sparsity, and LLM-constructed Graph-RAG incurs prohibitive costs. We propose \\textbf{\\fwa}, a unified framework that embeds unstructured text into structured knowledge graphs, creating a heterogeneous network for flexible evidence retrieval. Reasoning is formulated as adaptive structure induction, learned via a robust two-stage process: (1) imitation learning distills heuristic expert signals, and (2) reinforcement learning refines the policy using LLM-driven preference rewards. Experiments demonstrate that {\\fwa} effectively merges textual richness with structural knowledge, outperforming SOTA baselines in answer accuracy and reasoning fidelity while maintaining extremely low token costs and near real-time inference((code available at https://github.com/wjywjy123/HyGRL) .", "url": "https://wpnews.pro/news/hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-questions", "canonical_source": "https://www.machinebrief.com/news/hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-quest-ih4y", "published_at": "2026-07-23 04:00:00+00:00", "updated_at": "2026-07-23 05:34:44.055144+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "natural-language-processing"], "entities": ["HyGRL", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-questions", "markdown": "https://wpnews.pro/news/hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-questions.md", "text": "https://wpnews.pro/news/hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-questions.txt", "jsonld": "https://wpnews.pro/news/hygrl-adaptive-hybrid-graph-reasoning-for-multi-entity-questions.jsonld"}}