REAP：面向多跳问答的递归评估与自适应规划增强检索增强生成方法
REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
AI总结：
针对现有RAG在多跳推理中缺乏全局规划、检索内容利用不足的问题，本文提出REAP方法，通过SP与FE模块实现递归评估和自适应规划，结合统一多任务微调范式，在多跳问答任务上取得了优于现有方法的性能。
摘要：
检索增强生成（RAG）已被广泛用于缓解大语言模型（LLM）的幻觉问题。但现有面向多跳推理任务的方法往往缺乏全局规划，提升了陷入局部推理僵局的风险；同时对检索内容利用不足、忽略潜在线索，无法保障推理结果的准确性。为克服上述局限，本文提出递归评估与自适应规划方法REAP，其核心思路是通过子任务规划器（SP）和事实提取器（FE）模块，显式维护与当前任务相关的结构化子任务与事实。SP维持全局视角，基于FE的输出引导整体推理方向、评估任务状态，实现任务求解轨迹的动态优化；FE对检索内容进行细粒度分析，提取可靠答案与线索。两个模块逐步丰富逻辑连贯的全局知识表示，提升推理过程的可靠性与可追溯性。此外，本文提出统一任务范式设计，可实现高效多任务微调，显著提升SP在复杂、低数据量任务上的性能。本文在多个公开多跳数据集上开展了大量实验，结果表明所提方法在域内和域外设置下均显著优于现有RAG方法，验证了其在复杂多跳推理任务上的有效性。
英文摘要：
Retrieval-augmented generation (RAG) has been extensively employed to mitigate hallucinations in large language models (LLMs). However, existing methods for multi-hop reasoning tasks often lack global planning, increasing the risk of falling into local reasoning impasses. Insufficient exploitation of retrieved content and the neglect of latent clues fail to ensure the accuracy of reasoning outcomes. To overcome these limitations, we propose Recursive Evaluation and Adaptive Planning (REAP), whose core idea is to explicitly maintain structured sub-tasks and facts related to the current task through the Sub-task Planner (SP) and Fact Extractor (FE) modules. SP maintains a global perspective, guiding the overall reasoning direction and evaluating the task state based on the outcomes of FE, enabling dynamic optimization of the task-solving trajectory. FE performs fine-grained analysis over retrieved content to extract reliable answers and clues. These two modules incrementally enrich a logically coherent representation of global knowledge, enhancing the reliability and the traceability of the reasoning process. Furthermore, we propose a unified task paradigm design that enables effective multi-task fine-tuning, significantly enhancing SP's performance on complex, data-scarce tasks. We conduct extensive experiments on multiple public multi-hop datasets, and the results demonstrate that our method significantly outperforms existing RAG methods in both in-domain and out-of-domain settings, validating its effectiveness in complex multi-hop reasoning tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
