Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization
For practitioners of RAG systems, this work offers a simpler and more robust approach to error correction, avoiding the pitfalls of misaligned error taxonomies.
RePAIR improves retrieval-augmented generation by directly mapping flawed outputs to corrective actions without explicit error categorization, achieving consistent performance gains across multiple benchmarks.
Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge. Recent agentic RAG systems extend this paradigm with critical agents to evaluate model responses and iteratively refine outputs. However, most prior work implicitly assumes reliable critic feedback and focuses on planning strategies, while paying limited attention to the robustness of the error-correction process itself, which can be impacted by misaligned error categories and ineffective or incorrect corrections. Here, we hypothesize that RAG performance can be improved without explicit error categorization. We propose RePAIR, a response-action learning paradigm that directly maps flawed RAG outputs to error-mitigating action plans without relying on fine-grained error taxonomies and explicit critic supervision. Across multiple benchmarks, RePAIR consistently improves agentic RAG performance.