EvoGraph-R1：面向智能体检索的自演化多模态知识超图
EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval
把多模态知识图谱当作可被智能体动作（检索/扩展/编辑/终止）动态改写的环境，用 MDP 闭环驱动超图演化，为视觉问答中的多跳跨模态检索与可追溯推理提供了可复用的框架。
原文依据 We formulate retrieval as a Markov Decision Process (MDP) where the agent observes the graph state and executes actions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论检索增强生成（RAG）已成为将多模态大语言模型（MLLM）锚定于外部知识的关键范式。近期的 GraphRAG 方法引入结构化实体关系图以改进检索与推理。然而，这些方法仍受限于将知识图谱视为离线构建、单次查询的静态数据结构。这种静态范式与知识密集型推理的交互式、迭代式本质不相匹配，造成三个瓶颈：（i）以文本为中心的知识碎片化阻碍跨模态推理；（ii）冻结的结构无法纳入新证据或纠正错误；（iii）僵化的单次检索缺乏自适应精化。为克服这些局限，我们提出 EvoGraph-R1，一个自演化的 GraphRAG 框架，将知识图谱重新概念化为由智能体交互塑造的动态环境。我们将检索建模为马尔可夫决策过程（MDP），智能体在其中观察图状态并执行动作以查询（GraphRetrieve）、扩展（WebSearch）、精化（GraphEdit）或终止（Answer）推理。这些动作重塑超图结构并产生反馈信号以引导后续演化。通过这一闭环，超图通过整合新证据、纠正错误并精化结构来支持多跳推理，从而实现演化。在多模态视觉问答与文本问答基准上的实验表明，该方法在准确率、覆盖度与可追溯性上相较现有 RAG 基线取得显著提升，确立了自演化知识图谱作为跨模态基本范式的地位。
英文原文摘要 1645 字符
Retrieval-augmented generation (RAG) has emerged as a critical paradigm for grounding Multimodal Large Language Models (MLLMs) in external knowledge. Recent GraphRAG methods introduce structured entity-relation graphs to improve retrieval and reasoning. However, they remain limited by treating knowledge graphs as static data structures built offline and queried in a single pass. This static paradigm misaligns with the interactive, iterative nature of knowledge-intensive reasoning, creating three bottlenecks: (i) text-centric fragmentation that impedes cross-modal reasoning, (ii) frozen structures unable to incorporate new evidence or correct errors, and (iii) rigid single-pass retrieval without adaptive refinement. To overcome these limitations, we introduce EvoGraph-R1, a self-evolving GraphRAG framework that reconceptualizes knowledge graphs as dynamic environments shaped through agent interactions.We formulate retrieval as a Markov Decision Process (MDP) where the agent observes the graph state and executes actions to query (GraphRetrieve), expand (WebSearch), refine (GraphEdit), or terminate (Answer) the reasoning. These actions reshape the hypergraph structure and generate feedback signals that guide subsequent evolution.Through this closed loop, the hypergraph evolves by integrating new evidence, correcting errors, and refining structure to support multi-hop reasoning. Experiments on multimodal VQA and text QA benchmarks demonstrate substantial improvements over existing RAG baselines in accuracy, coverage, and traceability, establishing self-evolving knowledge graphs as a fundamental paradigm across modalities.