Doctor-RAG: Failure-Aware Repair for Agentic Retrieval-Augmented Generation

TL;DR

Doctor-RAG introduces a failure-aware repair framework for agentic retrieval-augmented generation, enabling precise error localization and minimal-cost correction to improve accuracy and efficiency in multi-hop question answering.

Contribution

It proposes a unified diagnose-and-repair method that localizes errors and repairs failures efficiently, reducing computational overhead in agentic RAG systems.

Findings

DR-RAG improves answer accuracy on multiple benchmarks.

It significantly reduces reasoning token consumption.

DR-RAG outperforms rerun-based repair strategies.

Abstract

Agentic Retrieval-Augmented Generation (Agentic RAG) has become a widely adopted paradigm for multi-hop question answering and complex knowledge reasoning, where retrieval and reasoning are interleaved at inference time. As reasoning trajectories grow longer, failures become increasingly common. Existing approaches typically address such failures by either stopping at diagnostic analysis or rerunning the entire retrieval-reasoning pipeline, which leads to substantial computational overhead and redundant reasoning. In this paper, we propose Doctor-RAG (DR-RAG), a unified diagnose-and-repair framework that corrects failures in Agentic RAG through explicit error localization and prefix reuse, enabling minimal-cost intervention. DR-RAG decomposes failure handling into two consecutive stages: (i) trajectory-level failure diagnosis and localization, which attributes errors to a coverage-gated taxonomy and identifies the earliest failure point in the reasoning trajectory; and (ii) tool-conditioned local repair, which intervenes only at the diagnosed failure point while maximally reusing validated reasoning prefixes and retrieved evidence. By explicitly separating error attribution from correction, DR-RAG enables precise error localization, thereby avoiding expensive full-pipeline reruns and enabling targeted, efficient repair. We evaluate DR-RAG across three multi-hop question answering benchmarks, multiple agentic RAG baselines, and different backbone models. Experimental results demonstrate that DR-RAG substantially improves answer accuracy while significantly reducing reasoning token consumption compared to rerun-based repair strategies.