PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering

• URL: http://arxiv.org/abs/2603.29085v1
• Date: Mon, 30 Mar 2026 23:52:54 GMT
• Title: PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
• Abstract summary: Large language models (LLMs) remain brittle on multi-hop question answering (MHQA)<n>We propose textbfPlanned Active Retrieval and Reasoning RAG (PAR$2$-RAG), a two-stage framework that separates emphcoverage from emphcommitment.
• Score: 57.89576196160413
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning [27.83191719981676]
  We present textscGTA-RAG, a graph-trajectory-augmented RL framework for retrieval-augmented reasoning.<n>Method consistently outperforms RL-based RAG baselines with both Qwen2.5-3B and Qwen2.5-7B backbones.
  arXiv  Detail & Related papers  (2026-08-23T16:05:20Z)
• Hierarchical Evidence-Driven Reasoning for Long Document Understanding [95.51688464037096]
  We introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding.<n>Our framework significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
  arXiv  Detail & Related papers  (2026-07-06T03:08:28Z)
• MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks [68.78064578688809]
  MTR-Suite is a unified framework for auditing, synthesizing, and benchmarking retrieval.<n>It features: (1) MTR-Eval, an LLM-based auditor quantifying alignment gaps in previous benchmarks; (2) MTR-Pipeline, a multi-agent system using greedy clustering to generate high-fidelity dialogues at 1/400th human cost; and (3) MTR-Bench, a rigorous general-domain benchmark.
  arXiv  Detail & Related papers  (2026-05-20T05:26:35Z)
• S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA [20.283357470094774]
  We propose S2G-RAG (Structured Sufficiency and Gap-judging RAG), an iterative framework with an explicit controller, S2G-Judge.<n>At each turn, S2G-Judge predicts whether the current evidence memory supports answering and, if not, outputs structured gap items that describe the missing information.<n>These gap items are then mapped into the next retrieval query, producing stable multi-turn retrieval trajectories.
  arXiv  Detail & Related papers  (2026-04-26T16:17:54Z)
• TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation [17.21708416305234]
  textscTaSR-RAG is a taxonomy-guided structured reasoning framework for evidence selection.<n>textscTaSR-RAG consistently outperforms strong RAG and structured-RAG baselines by up to 14%.
  arXiv  Detail & Related papers  (2026-03-10T08:16:36Z)
• Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly [1.2891210250935148]
  RAG systems often fail on multi-hop queries when the initial retrieval misses a bridge fact.<n>We propose textbfSEAL-RAG, a training-free controller that adopts a textbfreplace, don't expand'' strategy to fight context dilution.<n>We evaluate SEAL-RAG against faithful re-implementations of Basic RAG, CRAG, Self-RAG, and Adaptive-$k$ in a shared environment.
  arXiv  Detail & Related papers  (2025-12-11T16:31:29Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Evaluating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries [53.99620546358492]
  Real-world use cases often present RAG systems with complex queries for which relevant information is missing from the corpus or is incomplete.<n>Existing RAG benchmarks rarely reflect realistic task complexity for multi-hop or out-of-scope questions.<n>We present the first pipeline for automatic, difficulty-controlled creation of un$underlinec$heatable, $underliner$ealistic, $underlineu$nanswerable, and $underlinem$ulti-hop.
  arXiv  Detail & Related papers  (2025-10-13T21:38:04Z)
• Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking [31.73448933991891]
  Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs)<n>We propose T$2$RAG, a novel framework that operates on a simple, graph-free knowledge base of atomic triplets.<n> Empirical results show that T$2$RAG significantly outperforms state-of-the-art multi-round and Graph RAG methods.
  arXiv  Detail & Related papers  (2025-08-04T13:50:44Z)
• R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning [60.17074283370798]
  Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and hallucination.<n>We propose $textbfR3-RAG$, which uses $textbfR$einforcement learning to make the LLM learn how to $textbfR$eason and $textbfR$etrieve step by step, thus retrieving comprehensive external knowledge and leading to correct answers.
  arXiv  Detail & Related papers  (2025-05-26T12:25:37Z)
• FLARE: Faithful Logic-Aided Reasoning and Exploration [47.46564769245296]
  We introduce a novel approach for traversing the problem space using task decompositions.<n>We use the Large Language Models to plan a solution, soft-formalise the query into facts and predicates using a logic programming code.<n>Our method allows us to compute the faithfulness of the reasoning process w.r.t. the generated code and analyse the steps of the multi-hop search without relying on external solvers.
  arXiv  Detail & Related papers  (2024-10-14T19:39:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.