Lune

AAAI2026Top-tier venue

REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering

Yijie Zhu, Haojie Zhou, Wanting Hong, Tailin Liu, Ning Wang

Abstract

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-ofdomain settings, validating its effectiveness in complex multihop reasoning tasks.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Measuring and Narrowing the Compositionality Gap in Language Models cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy cites Measuring and Narrowing the Compositionality Gap in Language Models
  • Query Rewriting in Retrieval-Augmented Large Language Models cites Measuring and Narrowing the Compositionality Gap in Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on21

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. Measuring and Narrowing the Compositionality Gap in Language ModelsOfir Press, Muru Zhang, Sewon Min, Ludwig Schmidt et al.EMNLP Findings 2023 · 296 citations
  3. Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
  4. Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation SynergyZhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang et al.EMNLP Findings 2023 · 200 citations
  5. Query Rewriting in Retrieval-Augmented Large Language ModelsXinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao et al.EMNLP 2023 · 191 citations

Related papers

  1. Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTSShijia Xu, Zhou Wu, Xiaolong Jia, Yu Wang et al.ACL Findings 2026
  2. GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language ModelsJialin Chen, Houyu Zhang, Seongjun Yun, Alejandro Mottini et al.EMNLP Findings 2025 · 3 citations
  3. A Survey of RAG-Reasoning Systems in Large Language ModelsYangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang et al.EMNLP Findings 2025 · 9 citations
  4. OPERA: A Reinforcement Learning-Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop RetrievalYu Liu, Yanbing Liu, Fangfang Yuan, Cong Cao et al.AAAI 2026 · 4 citations
  5. You Don't Need Pre-Built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning StructuresShengyuan Chen, Chuang Zhou, Zheng Yuan, Qinggang Zhang et al.AAAI 2026 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines