圖譜顧問：通過多智能體協同實現自適應圖譜探索以增強大語言模型推理能力

Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning

June 4, 2025

作者: Junqi Gao, Xiang Zou, YIng Ai, Dong Li, Yichen Niu, Biqing Qi, Jianxing Liu

cs.AI

摘要

圖檢索增強生成（Graph Retrieval Augmented Generation, GraphRAG）通過顯式建模知識關係，有效提升了大型語言模型（Large Language Models, LLMs）在專業領域中的外部知識整合能力，從而改善了生成內容的事實準確性與質量。然而，現有方法存在兩大固有局限：其一，信息聚合效率低下，依賴單一代理與固定迭代模式，難以自適應地捕捉圖數據中的多層次文本、結構及度信息；其二，推理機制僵化，採用預設推理方案，無法動態調整推理深度，亦無法實現精確的語義校正。為克服這些局限，我們提出了基於多代理協作的GraphRAG方法——圖顧問（Graph Counselor）。該方法利用自適應圖信息提取模塊（Adaptive Graph Information Extraction Module, AGIEM），其中規劃、思考與執行代理協同工作，精確建模複雜圖結構並動態調整信息提取策略，解決了多層次依賴建模與自適應推理深度的挑戰。此外，多視角自我反思（Self-Reflection with Multiple Perspectives, SR）模塊通過自我反思與逆向推理機制，提升了推理結果的準確性與語義一致性。實驗表明，Graph Counselor在多項圖推理任務中均優於現有方法，展現出更高的推理準確性與泛化能力。我們的代碼已公開於https://github.com/gjq100/Graph-Counselor.git。

English

Graph Retrieval Augmented Generation (GraphRAG) effectively enhances external knowledge integration capabilities by explicitly modeling knowledge relationships, thereby improving the factual accuracy and generation quality of Large Language Models (LLMs) in specialized domains. However, existing methods suffer from two inherent limitations: 1) Inefficient Information Aggregation: They rely on a single agent and fixed iterative patterns, making it difficult to adaptively capture multi-level textual, structural, and degree information within graph data. 2) Rigid Reasoning Mechanism: They employ preset reasoning schemes, which cannot dynamically adjust reasoning depth nor achieve precise semantic correction. To overcome these limitations, we propose Graph Counselor, an GraphRAG method based on multi-agent collaboration. This method uses the Adaptive Graph Information Extraction Module (AGIEM), where Planning, Thought, and Execution Agents work together to precisely model complex graph structures and dynamically adjust information extraction strategies, addressing the challenges of multi-level dependency modeling and adaptive reasoning depth. Additionally, the Self-Reflection with Multiple Perspectives (SR) module improves the accuracy and semantic consistency of reasoning results through self-reflection and backward reasoning mechanisms. Experiments demonstrate that Graph Counselor outperforms existing methods in multiple graph reasoning tasks, exhibiting higher reasoning accuracy and generalization ability. Our code is available at https://github.com/gjq100/Graph-Counselor.git.