让大模型逐步积累证据，提升问答稳定性。
Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
- 将检索文档转为带置信度的结构化推理单元，持久保存证据。
- 通过迭代分析缺失与矛盾，持续优化查询，稳定积累高质量证据。
- 适合需要高鲁棒性的复杂问答场景，尤其在噪声检索下表现优异。
检索增强生成（RAG）将大语言模型（LLM）锚定于外部知识，但常因上下文表示扁平和无状态检索导致性能不稳定。我们提出具有迭代推理的状态化证据驱动RAG框架，将问答建模为渐进式证据积累过程。检索到的文档被转化为包含明确相关性与置信度信号的结构化推理单元，并存入持久证据池，以保留支持与非支持信息。该框架执行证据驱动的缺陷分析，识别信息缺口与冲突，并迭代优化查询以引导后续检索。这种迭代推理过程实现了稳定的证据聚合，增强了对噪声检索的鲁棒性。在多个问答基准上的实验表明，该方法持续优于标准RAG与多步基线，有效积累高质量证据，并在大量检索噪声下保持稳定性能。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful Evidence-Driven RAG with Iterative Reasoning, a framework that models question answering as a progressive evidence accumulation process. Retrieved documents are converted into structured reasoning units with explicit relevance and confidence signals and maintained in a persistent evidence pool capturing both supportive and non-supportive information. The framework performs evidence-driven deficiency analysis to identify gaps and conflicts and iteratively refines queries to guide subsequent retrieval. This iterative reasoning process enables stable evidence aggregation and improves robustness to noisy retrieval. Experiments on multiple question answering benchmarks demonstrate consistent improvements over standard RAG and multi-step baselines, while effectively accumulating high-quality evidence and maintaining stable performance under substantial retrieval noise.
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。