提出分阶段检索与推理框架，提升多跳问答准确率。
PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
- 先广度搜索构建高召回证据边界，再深度精炼控制证据充分性。
- 在四个基准上最高比现有方法准确率提升23.5%，检索指标提升10.5%。
- 适合需要精准多文档推理的复杂问答场景。
大型语言模型在多跳问答（MHQA）任务中仍表现脆弱，需跨文档整合证据并进行推理。迭代检索系统可能因早期低召回路径锁定而放大下游错误，而仅依赖规划的方法则生成静态查询集，无法随中间证据变化调整。本文提出【计划式主动检索与推理RAG（PAR$^2$-RAG）】，采用两阶段框架，将【覆盖】与【承诺】分离：第一阶段采用广度优先锚定，构建高召回证据前沿；第二阶段通过深度优先精炼与证据充分性控制，在迭代循环中持续优化。在四个MHQA基准测试中，PAR$^2$-RAG始终优于现有最先进基线，相比IRCoT，准确率最高提升23.5%，检索指标NDCG最高提升10.5%。
原文摘要 · Abstract (English)
Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. Iterative retrieval systems can fail by locking onto an early low-recall trajectory and amplifying downstream errors, while planning-only approaches may produce static query sets that cannot adapt when intermediate evidence changes. We propose \textbf{Planned Active Retrieval and Reasoning RAG (PAR$^2$-RAG)}, a two-stage framework that separates \emph{coverage} from \emph{commitment}. PAR$^2$-RAG first performs breadth-first anchoring to build a high-recall evidence frontier, then applies depth-first refinement with evidence sufficiency control in an iterative loop. Across four MHQA benchmarks, PAR$^2$-RAG consistently outperforms existing state-of-the-art baselines, compared with IRCoT, PAR$^2$-RAG achieves up to \textbf{23.5\%} higher accuracy, with retrieval gains of up to \textbf{10.5\%} in NDCG.
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。