Skip to content
Preprint

HyGRL: Adaptive Hybrid Graph Reasoning for Multi-Entity Questions

Jul 2026 · 0 citations · 39 references
Computer Science

TL;DR

A unified framework that embeds unstructured text into structured knowledge graphs, creating a heterogeneous network for flexible evidence retrieval, outperforming SOTA baselines in answer accuracy and reasoning fidelity while maintaining extremely low token costs and near real-time inference is proposed.

Abstract

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) .

View source

Similar papers

Preprint Jul 2026

EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval

EvoGraph-R1 is introduced, a self-evolving GraphRAG framework that reconceptualizes knowledge graphs as dynamic environments shaped through agent interactions, establishing self-evolving knowledge graphs as a fundamental paradigm across modalities.

Jiashi Lin, Changhong Jiang, Xiangru Lin et al. · 1 citation
Conference Open access 2026

MuSe: Multi-Stage Graph Reasoning via Vision-Language Models

This work proposes MuSe, a novel multi-stage graph reasoning framework based on VLMs, where instead of processing entire graphs at once, MuSe incrementally samples and visualizes task-relevant subgraphs, enabling progressive reasoning.

Guanyu Wang, Xu Chu, Zhijie Tan et al. · 1 citation
Preprint Aug 2026

SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation

Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often underuse the relational structure encoded in knowledge graphs. Graph-based RAG can capture entity relationships, yet supervised graph retrieval typically requires labeled question-answer data that may not be available for newly constructed graphs. We address this limitation with SelfGraphRAG, a framework that generates question-answer pairs directly from knowledge graph structure and uses them to train a query-conditioned graph retriever. The generated questions capture multi-hop paths and local neighborhoods, providing relational supervision without manual annotation. Experiments on multi-hop question answering and classification benchmarks show that SelfGraphRAG improves retrieval precision and downstream reasoning performance over embedding-based baselines. These results suggest that knowledge graph structure can provide useful supervision for training graph retrievers when labeled data are unavailable.

Ben Lagnese, Manas Gaur · 0 citations
Preprint Aug 2026

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning

This paper proposes DocTrace, a hierarchical framework that progressively performs evidence localization, structured document parsing, and evidence graph reasoning to enable explicit evidence provenance, and develops a two-stage training framework.

Lei Xiang, Zhicheng Guan, Hong Chen et al. · 0 citations
Book Open access Aug 2026

NaviRAG: Learning to Navigate Knowledge Graphs for Retrieval-Augmented Generation

NaviRAG is a novel framework that reformulates retrieval as a reinforcement learning-driven dynamic navigation problem on schema-less knowledge graphs (KGs), achieving state-of-the-art performance in multi-hop QA while maintaining robustness in single-hop QA.

Jinghong Lei, Wang Kun, Zhigang Chen et al. · 0 citations
Conference Open access 2026

Query-Aware Knowledge Retrieval via Hyperbolic Structuring

HyperRAG is introduced, a novel framework in the Hyper-bolic space that captures both explicit entity-based links and implicit query-aware connections and consistently outperforms existing baselines.

Chuang Zhou, Junnan Dong, Yilin Xiao et al. · 0 citations