思图3.0：基于多智能体双演进上下文检索的异构图高效自适应大语言模型推理

摘要

檢索增強生成（Retrieval-Augmented Generation, RAG）及基於圖的RAG已成為利用外部知識增強大型語言模型（Large Language Models, LLMs）的重要範式。然而，現有方法面臨一個根本性的權衡：基於圖的方法本質上依賴於高質量的圖結構，但卻受到顯著的實際限制——手動構建的知識圖譜在擴展上成本過高，而從語料庫中自動提取的圖則受限於底層LLM提取器的性能，尤其是在使用較小、本地部署的模型時。本文提出了Think-on-Graph 3.0（ToG-3），這是一個新穎的框架，引入了多智能體上下文演化與檢索（Multi-Agent Context Evolution and Retrieval, MACER）機制以克服這些限制。我們的核心創新在於動態構建並精煉一個Chunk-Triplets-Community異構圖索引，該索引首次融合了查詢演化與子圖演化的雙重演化機制，以實現精確的證據檢索。這一方法解決了先前基於圖的RAG方法的一個關鍵限制，即通常一次性構建靜態圖索引而不適應實際查詢。一個由構造者、檢索者、反思者與響應者智能體組成的多智能體系統，協同參與證據檢索、答案生成、充分性反思，以及至關重要的查詢與子圖演化的迭代過程。這種雙重演化的多智能體系統使ToG-3能夠在推理過程中自適應地構建目標圖索引，緩解了靜態一次性圖構建的固有缺陷，並使得即使使用輕量級LLM也能進行深度精確的推理。大量實驗表明，ToG-3在深度與廣度推理基準上均優於對比基線，而消融研究則證實了MACER框架各組件的有效性。

English

Retrieval-Augmented Generation (RAG) and Graph-based RAG has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches face a fundamental trade-off. While graph-based methods are inherently dependent on high-quality graph structures, they face significant practical constraints: manually constructed knowledge graphs are prohibitively expensive to scale, while automatically extracted graphs from corpora are limited by the performance of the underlying LLM extractors, especially when using smaller, local-deployed models. This paper presents Think-on-Graph 3.0 (ToG-3), a novel framework that introduces Multi-Agent Context Evolution and Retrieval (MACER) mechanism to overcome these limitations. Our core innovation is the dynamic construction and refinement of a Chunk-Triplets-Community heterogeneous graph index, which pioneeringly incorporates a dual-evolution mechanism of Evolving Query and Evolving Sub-Graph for precise evidence retrieval. This approach addresses a critical limitation of prior Graph-based RAG methods, which typically construct a static graph index in a single pass without adapting to the actual query. A multi-agent system, comprising Constructor, Retriever, Reflector, and Responser agents, collaboratively engages in an iterative process of evidence retrieval, answer generation, sufficiency reflection, and, crucially, evolving query and subgraph. This dual-evolving multi-agent system allows ToG-3 to adaptively build a targeted graph index during reasoning, mitigating the inherent drawbacks of static, one-time graph construction and enabling deep, precise reasoning even with lightweight LLMs. Extensive experiments demonstrate that ToG-3 outperforms compared baselines on both deep and broad reasoning benchmarks, and ablation studies confirm the efficacy of the components of MACER framework.

思图3.0：基于多智能体双演进上下文检索的异构图高效自适应大语言模型推理

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

摘要

Support