不依赖错误分类，直接学习修正策略提升RAG准确性
Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization
- 直接映射错误输出到纠正动作，跳过细粒度分类
- 多基准测试中显著提升智能体RAG性能
- 适合追求稳定纠错效果的工程应用
检索增强生成（RAG）通过引入外部知识提升大语言模型输出的事实准确性。近期的智能体RAG系统引入关键评估代理，对模型输出进行评价并迭代优化。然而，以往研究普遍假设评估反馈可靠，侧重于规划策略，却较少关注纠错过程本身的鲁棒性——这可能受错误类别错位、无效或错误修正的影响。本文提出RePAIR，一种响应-动作学习范式，直接将有缺陷的RAG输出映射为缓解错误的动作计划，无需细粒度错误分类和显式批评监督。在多个基准测试中，RePAIR均持续提升智能体RAG表现。
原文摘要 · Abstract (English)
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.
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。