让AI问答出错时能自动定位并精准修复，避免重复计算。
Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation
- 分两阶段诊断错误并局部修复，不重跑全程。
- 在多个测试集上准确率显著提升，最高增益达12.3%。
- 适合需要可靠推理的复杂问答系统开发者使用。
智能体增强型生成模型在多跳问答和复杂知识任务中通过交替检索与推理来工作。随着推理路径变长，错误出现频率上升。现有方法常仅停留在错误诊断或依赖粗粒度重规划与重新运行，导致计算成本过高。本文提出Doctor-RAG（DR-RAG），一种诊断-修复框架，通过显式错误定位与前缀复用实现故障纠正。该框架包含两个阶段：(i) 路径级失败诊断，采用轻量诊断模型联合评估证据充分性、分类失败类型并定位最早失败点；(ii) 工具条件下的局部修复，在诊断点进行干预，同时复用符合条件的前缀和已检索证据。通过将错误归因与修正分离，DR-RAG避免了事后修复中的盲目重跑，实现了对已知失败路径的精准高效修正。在三个多跳问答基准上，针对多种代理RAG基线与主干模型的实验表明，答案准确率得到显著提升。
原文摘要 · Abstract (English)
Agentic Retrieval-Augmented Generation interleaves retrieval and reasoning for multi-hop QA and complex knowledge tasks. As reasoning trajectories lengthen, failures become more frequent, while existing methods often either stop at diagnosis or rely on coarse replanning and rerun-style recovery, incurring high computational cost. We propose DoctorRAG (DR-RAG), a diagnose-and-repair framework that corrects failures via explicit error localization and prefix reuse. DR-RAG operates in two stages: (i) trajectory-level failure diagnosis, where a distilled diagnosis model jointly assesses evidence sufficiency, classifies the failure type, and localizes the earliest failure point; and (ii) tool-conditioned local repair that intervenes only at the diagnosed point while reusing conditionally valid prefixes and retrieved evidence. By separating error attribution from correction, DR-RAG avoids blind reruns in a post-hoc repair setting and enables targeted, efficient correction of known failed trajectories. Experiments on three multi-hop QA benchmarks across multiple agentic RAG baselines and backbone models show substantial improvements in answer accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。