失败是反馈：面向多模态图中代理遍历的历史感知回溯
Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal Graphs
AI总结：
FiF通过历史感知回溯和经济理性的代理工作流程，提升多模态图中检索的适应性和效率。
摘要：
开放域多模态文档检索旨在从大规模且相互关联的文档语料库中检索特定组件（段落、表格或图像）。现有的基于图的检索方法通常依赖于统一的相似性度量，忽略了跳跃特定语义，其刚性的预定义计划阻碍了动态错误纠正。这些限制表明，检索器应适应不断变化的上下文并从死胡同中智能恢复。为了解决这些需求，我们提出了Failure is Feedback（FiF），将子图检索视为一个连续决策过程，并引入了两个关键创新。（i）我们引入了历史感知回溯机制；不同于标准回溯仅简单地回退状态，我们的方法利用失败遍历的上下文，借鉴先前失败的见解。（ii）我们实现了经济理性的代理工作流程。不同于传统具有静态策略的代理，我们的协调器采用成本感知的遍历方法，动态管理检索准确性和推理成本之间的权衡，并在先前失败证明额外计算投入值得时升级到高强度LLM推理。大量实验表明，FiF在MultimodalQA、MMCoQA和WebQA基准上实现了最先进的检索性能。
英文摘要：
Open-domain multimodal document retrieval aims to retrieve specific components (paragraphs, tables, or images) from large and interconnected document corpora. Existing graph-based retrieval approaches typically rely on a uniform similarity metric that overlooks hop-specific semantics, and their rigid pre-defined plans hinder dynamic error correction. These limitations suggest that a retriever should adapt its reasoning to the evolving context and recover intelligently from dead ends. To address these needs, we propose Failure is Feedback (FiF), which casts subgraph retrieval as a sequential decision process and introduces two key innovations. (i) We introduce a history-aware backtracking mechanism; unlike standard backtracking that simply reverts the state, our approach piggybacks on the context of failed traversals, leveraging insights from previous failures. (ii) We implement an economically-rational agentic workflow. Unlike conventional agents with static strategies, our orchestrator employs a cost-aware traversal method to dynamically manage the trade-off between retrieval accuracy and inference costs, escalating to intensive LLM-based reasoning only when the prior failure justifies the additional computational investment. Extensive experiments show that FiF achieves state-of-the-art retrieval on the benchmarks of MultimodalQA, MMCoQA and WebQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
