Multi-Hop QA

QA: Question Answering

Ask about this topic

Overview

Multi-hop question answering asks systems to connect several facts or sources, often through intermediate entities or sub-questions, instead of finding an answer in a single passage. Common approaches decompose questions into steps, use iterative retrieval-augmented generation, or follow paths through knowledge graphs, with verification and evidence tracking to keep each step grounded. Benchmarks such as HotpotQA, MuSiQue, and 2WikiMultiHopQA test linked evidence across documents, while newer evaluations extend to long, multimodal, and domain-specific collections. A central challenge is distinguishing failures to find evidence from failures to combine or verify evidence that was retrieved, while controlling the cost of additional searches and reasoning.

Latest papers

CardsList

229 papers24 papers in the last four weeks, down 27% on the four weeks before. 0.1% of all new papers.

May 12, 2026

MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering

Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circulated exam-style datasets are increasingly vulnerable to performance saturation and training data contamination. Multi-hop reasoning, defined as the ability to integrate information across multiple sources to derive an answer, is central to clinically meaningful tasks such as diagnostic support, literature-based discovery, and hypothesis generation, yet remains underrepresented in current biomedical QA benchmarks. MedHopQA is a disease-centered multi-hop reasoning benchmark consisting of 1,000 expert-curated question-answer pairs introduced as a shared task at BioCreative IX. Each question requires synthesis of information across two distinct Wikipedia articles, and answers are provided in an open-ended free-text format. Gold annotations are augmented with ontology-grounded synonym sets from MONDO, NCBI Gene, and NCBI Taxonomy to support both lexical and concept-level evaluation. MedHopQA was constructed through a structured process combining human annotation, triage, iterative verification, and LLM-as-a-judge validation. To reduce leaderboard gaming and contamination risk, the 1,000 scored questions are embedded within a publicly downloadable set of 10,000 questions, with answers withheld, on a CodaBench leaderboard. MedHopQA provides both a benchmark and a reusable framework for constructing future biomedical QA datasets that prioritize compositional reasoning, saturation resistance, and contamination resistance as core design constraints.

Rezarta Islamaj, Robert Leaman, Joey Chan +13

National Library of Medicine, Division of Intramural Research, Bethesda, MD, US · University of Illinois at Urbana-Champaign, Department of Computer Science, Urbana, IL, US · University of Michigan Medical School, Ann Arbor, Michigan, US

Multi-Hop QALLM EvaluationHealthcareBiomedical QA
AskPDF
May 12, 2026

Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering

Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex questions. To address this problem, the BioCreative IX MedHopQA shared task was designed to benchmark in multi-hop reasoning for large language models (LLMs). We developed a novel dataset of 1,000 challenging QA pairs spanning diseases, genes, and chemicals, with particular emphasis on rare diseases. Each question was constructed to require two-hop reasoning through the integration of information from two distinct Wikipedia pages. The challenge attracted 48 submissions from 13 teams. Systems were evaluated using both surface string comparison and conceptual accuracy (MedCPT score). The results showed a substantial performance gap between baseline LLMs and enhanced systems. The top-ranked submission achieved an 89.30% F1 score on the MedCPT metric and an 87.30% exact match (EM) score, compared with 67.40% and 60.20%, respectively, for the zero-shot baseline. A central finding of the challenge was that retrieval-augmented generation (RAG) and related retrieval-based strategies were critical for strong performance. In addition, concept-level evaluation improved answer assessment when correct responses differed in surface form. The MedHopQA dataset is publicly available to support continued progress in this important area. Challenge materials: https://www.ncbi.nlm.nih.gov/research/bionlp/medhopqa and benchmark https://www.codabench.org/competitions/7609/

Rezarta Islamaj, Joey Chan, Robert Leaman +13

National Library of Medicine (NLM), National Institutes of Health (NIH), MD, 20894, Bethesda, USA · University of Illinois at Urbana Champaign · Korea University +7

Multi-Hop QAHealthcareBiomedical QARAG Evaluation
AskPDF
May 12, 2026

Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems

LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are increasingly adopted to overcome this limitation by storing interactions in external memory modules and performing retrieval from them, their effectiveness in answering challenging questions (e.g., multi-hop, commonsense) ultimately depends on the agent's ability to reason over the retrieved information. However, existing methods typically retrieve memory based on semantic similarity to the raw user utterance, which lacks explicit reasoning about missing intermediate facts and often returns evidence that is irrelevant or insufficient for grounded reasoning. In this work, we introduce Goal-Mem, a goal-oriented reasoning framework for RAG-based agentic memory that performs explicit backward chaining from the user's utterance as a goal. Rather than progressively expanding from retrieved context, Goal-Mem decomposes each goal into atomic subgoals, performs targeted memory retrieval to satisfy each subgoal, and iteratively identifies what information from memory should be retrieved when intermediate goals cannot be resolved. We formalize this process in Natural Language Logic, a logical system that combines the verifiability of reasoning provided by FOL with the expressivity of natural language. Through extensive experiments on two datasets and comparing to nine strong memory baselines, we show that Goal-Mem consistently improves performance, particularly on tasks requiring multi-hop reasoning and implicit inference.

Jiazhou Liang, Armin Toroghi, Yifan Simon Liu +3

University of Toronto · Vector Institute for Artificial Intelligence

Multi-Hop QAAgentic RAGLong-Term Conversational MemoryLLM Reasoning
AskPDF
May 10, 2026

HOME-KGQA: A Benchmark Dataset for Multimodal Knowledge Graph Question Answering on Household Daily Activities

Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured knowledge. Integrating these two in a complementary manner enables the development of reliable and verifiable AI systems. In particular, knowledge graph question answering (KGQA) has attracted attention as a means to reduce LLM hallucinations and to leverage knowledge beyond the training data. However, existing KGQA benchmark datasets are biased toward encyclopedic knowledge, limited to a single modality, and lack fine-grained spatiotemporal data, which limits their applicability to real-world scenarios targeted by Embodied AI. We introduce HOME-KGQA, a novel KGQA benchmark dataset built on a multimodal KG of daily household activities. HOME-KGQA consists of complex, multi-hop natural language questions paired with graph database query languages. Compared to existing benchmarks, it includes more challenging questions that involve multi-level spatiotemporal reasoning, multimodal grounding, and aggregate functions. Experimental results show that the LLM-based KGQA methods fail to achieve performance comparable to that on existing datasets when evaluated on HOME-KGQA. This highlights significant challenges that should be addressed for the real-world deployment of KGQA systems. Our dataset is available at https://github.com/aistairc/home-kgqa

Shusaku Egami, Aoi Ohta, Tomoki Tsujimura +5

National Institute of Advanced Industrial Science and Technology (AIST) Koto-ku, Tokyo, Japan

Multi-Hop QASpatiotemporal ReasoningEmbodied QAKnowledge Graph Question AnsweringMultimodal KGs
AskPDF
May 9, 2026

Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search

Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively search for cross-modal evidence remains underexplored. In this paper, we introduce Omni-DeepSearch, a benchmark for audio-driven omni-modal deep search. Given one or more audio clips and a related question, models must infer useful clues from audio, invoke text, image, and video search tools, and perform multi-hop reasoning to produce a short, objective, and verifiable answer. Omni-DeepSearch contains 640 samples across 15 fine-grained categories, covering four retrieval target modalities and four audio content types. A multi-stage filtering pipeline ensures audio dependence, retrieval necessity, visual modality necessity, and answer uniqueness. Experiments on recent closed-source and open-source omni-modal models show that this task remains highly challenging: the strongest evaluated model, Gemini-3-Pro, achieves only 43.44% average accuracy. Further analyses illustrate key bottlenecks in audio entity inference, query formulation, tool-use reliability, multi-hop retrieval, and cross-modal verification. These results highlight audio-driven omni-modal deep search as an important and underexplored direction for future multimodal agents.

Tao Yu, yiming ding, Shenghua Chai +16

CASIA · UCAS · BAAI +2

Multi-Hop QAMultimodal IRAudio UnderstandingMultimodal QAMultimodal Search AgentsMultimodal Model Evaluation+1
AskPDF
May 7, 2026

Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents

Self-evolving search agents reduce reliance on human-written training questions by generating and solving their own search tasks. We build on Search Self-Play (SSP), a representative Proposer and Solver framework in which questions are generated and answered via multi-step search and reasoning. In practice, however, SSP faces two bottlenecks: the Proposer constructs questions from isolated answer entities without relational context, yielding many invalid or unverifiable questions in early self-play training, while the Solver receives only a binary outcome reward that discards useful signal from partially on-track search trajectories. We address both bottlenecks by reusing knowledge-graph paths as construction-derived intermediate supervision for both question construction and reward shaping. First, we ground question construction in LLM-guided knowledge-graph subgraphs, providing relational context for the Proposer. Second, we observe that constructing and solving a multi-hop question can involve overlapping intermediate entities: the factual bridges used to formulate the question may provide approximate waypoints for answering it. Exploiting this overlap, we introduce Waypoint Coverage Reward (WCR), which grants graded partial credit to incorrect Solver trajectories according to their coverage of entities on the construction path, while preserving full reward for correct answers. Across seven QA benchmarks and nine model configurations, our approach improves the average score over standard SSP in all configurations, including notable gains on multi-hop QA tasks. These results suggest that knowledge-graph paths can be reused as lightweight intermediate supervision, providing both relational guidance and process feedback without additional task-specific human annotations or manually labeled process steps.

Huyu Wu, Jun Liu, Xiaochi Wei +3

Xiaohongshu Inc., Beijing, China

Multi-Hop QAReward ShapingSelf-Evolving Agents
AskPDF
May 7, 2026

Inference-Time Budget Control for LLM Search Agents

LLM search agents increasingly rely on tools at inference time, but their trajectories are often constrained by hard limits on both tool calls and generated tokens. Under such dual budgets, better answers require not only stronger models, but also explicit control over which search action should receive the next budget unit and when the accumulated evidence is sufficient to commit a final answer. We study this problem in multi-hop question answering (QA) and formulate it as two-stage inference-time budget control. At search time, our controller assigns each feasible action a task-level Value-of-Information (VOI) score, defined as an operational estimate of marginal task value per unit budget under the current search state and remaining dual budget, and uses this score to choose among retrieval, decomposition, and answer commitment. After search, a selective evidence-grounded finalizer compares the trajectory answer with a refined candidate and rewrites only when the residual error appears to be a low-risk answer-form error. Across four multi-hop QA benchmarks, three LLM backbones, and four budget levels, the method yields positive aggregate gains over four audited baselines under the same hard dual-budget protocol. Ablations show that search-time budget control, especially budget-dependent penalty, provides the main performance gain, while answer-time control helps mainly when the retrieval path is already adequate. These results suggest that inference-time budget control for LLM search agents should govern both how budget is spent during search and how the final answer is committed.

Zhengru Fang, Senkang Forest Hu, Zhonghao Chang +6

City University of Hong Kong · Tsinghua University · Alibaba Ant Group

Multi-Hop QAInference-Time SearchCost-Aware InferenceLLM Agents
AskPDF
May 5, 2026

Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA

The MedHopQA challenge presents a critical test for Large Language Models (LLMs): complex, multi-hop reasoning in the high-stakes biomedical domain. This paper details our direct API-based evaluation of Google's Gemini Flash models, focusing on the impact of advanced prompt engineering. We designed a sophisticated, multi-component prompt for Gemini 2.0 Flash that combined role-playing, explicit multi-shot Chain-of-Thought (CoT) examples, and detailed formatting rules. Our best run, using this complex prompt, achieved a Concept Level Score of 0.720. This result dramatically outperformed a baseline prompt which scored only 0.565. Remarkably, this performance on the efficient Gemini 2.0 Flash was almost identical to the result from the next-generation Gemini 2.5 Flash. Our findings demonstrate that sophisticated prompt design is a critical factor for unlocking the full reasoning capabilities of modern LLMs.

Ahmed Bajaber, Mohammed Alliheedi

1Saudi Med AI Lab (SMAIL) 2Prince Sultan University, Riyadh, Saudi Arabia · 2Prince Sultan University, Riyadh, Saudi Arabia · 3Al-Baha University, Al Baha, Saudi Arabia

Multi-Hop QALLM EvaluationLLM PromptingBiomedical QAFew-Shot Prompting
AskPDF
May 4, 2026

AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) remains brittle on multi-hop questions in realistic deployment settings, where retrieved evidence may be noisy or redundant and only limited context can be passed to the generator. Existing controllers address parts of this problem, but typically either expand context additively, select from a fixed top-k set, or optimize relevance without explicitly repairing missing bridge facts. We propose AdaGATE, a training-free evidence controller for multi-hop RAG that frames evidence selection as a token-constrained repair problem. AdaGATE combines entity centric gap tracking, targeted micro-query generation, and a utility based selection mechanism that balances gap coverage, corroboration, novelty, redundancy, and direct question relevance. We evaluate AdaGATE on HotpotQA under clean, redundancy, and noise injected retrieval conditions. Across all three settings, AdaGATE achieves the best evidence F1 among the compared controllers, reaching 62.3% on clean data and 71.2% under redundancy injection, while using 2.6x fewer input tokens than Adaptive-k. These results suggest that explicit gap-aware repair, combined with token-efficient evidence selection, improves robustness in multi-hop RAG under imperfect retrieval. Our code and evaluation pipeline are available at https://github.com/eliguo/AdaGATE.

Yilin Guo, Yinshan Wang, Yixuan Wang

Center for Data Science New York University · Tandon School of Engineering New York University

Multi-Hop QARetrieval-Augmented GenerationAdaptive RAGEvidence SelectionRetrieval RobustnessRAG Robustness
AskPDF
May 2, 2026

S3S^3-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data

Reinforcement learning (RL) post-training has enabled newer capabilities in models, such as agentic tool-use for search. However, these models struggle primarily due to limitations with sparse outcome-based rewards and a lack of training data that encapsulates questions of differing hardness, which results in models not performing deeper searches with tools to collect evidence for question-answering. To address these limitations, we introduce S^3-R1 (Synthetic data and stabilized Search R1), a framework that couples a data-centric approach with denser learning signals. We first develop a synthetic generation and curation pipeline that programmatically derives diverse, multi-hop questions from existing documents. This pipeline incorporates a retrieval-based verification step to specifically isolate questions of intermediate difficulty. We then pair this expanded training set with a reward structure that evaluates both intermediate search quality and the correctness of the final answer. This setup directly mitigates the credit assignment problems inherent to sparse rewards. Our evaluations show that S^3-R1 outperforms existing baselines by learning more effective search and synthesis strategies, yielding up to a 10% improvement in robust generalization on out-of-domain datasets.

Harsh Goel, Akhil Udathu, Susmija Jabbireddy +2

The University of Texas at Austin · Work done during an internship at Google DeepMind · Google DeepMind

Multi-Hop QASynthetic Data GenerationAgentic RAGSparse-Reward RLRL for Tool Use
AskPDF
May 1, 2026

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods designed for single-document retrieval face critical challenges in scaling to cross-document multi-hop questions: (1) poor distribution adaptability, where kk-means clustering introduces noise due to rigid distribution assumptions; (2) structural isolation, as tree indexes lack explicit cross-document connections; and (3) coarse abstraction, which obscures fine-grained details. To address these limitations, we propose ΨΨ-RAG, a tree-RAG framework with two key components. First, a hierarchical abstract tree index built through an iterative "merging and collapse" process that adapts to data distributions without a priori assumption. Second, a multi-granular retrieval agent that intelligently interacts with the knowledge base with reorganized queries and an agent-powered hybrid retriever. ΨΨ-RAG supports diverse tasks from token-level question answering to document-level summarization. On cross-document multi-hop QA benchmarks, it outperforms RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1 score. Code is available at https://github.com/Newiz430/Psi-RAG.

Ziwen Zhao, Menglin Yang

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China.

Multi-Hop QARetrieval-Augmented Generation
AskPDF
Apr 30, 2026

NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains

Although precise recall is a core objective in Retrieval-Augmented Generation (RAG), a critical oversight persists in the field: improvements in retrieval performance do not consistently translate to commensurate gains in downstream reasoning. To diagnose this gap, we propose the Recall Conversion Rate (RCR), a novel evaluation metric to quantify the contribution of retrieval to reasoning accuracy. Our quantitative analysis of mainstream RAG methods reveals that as Recall@5 improves, the RCR exhibits a near-linear decay. We identify the neglect of retrieval quality in these methods as the underlying cause. In contrast, approaches that focus solely on quality optimization often suffer from inferior recall performance. Both categories lack a comprehensive understanding of retrieval quality optimization, resulting in a trade-off dilemma. To address these challenges, we propose comprehensive retrieval quality optimization criteria and introduce the NeocorRAG framework. This framework achieves holistic retrieval quality optimization by systematically mining and utilizing Evidence Chains. Specifically, NeocorRAG first employs an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence chain generation through constrained decoding. Finally, the retrieved set of evidence chains guides the retrieval optimization process. Evaluated on benchmarks including HotpotQA, 2WikiMultiHopQA, MuSiQue, and NQ, NeocorRAG achieves SOTA performance on both 3B and 70B parameter models, while consuming less than 20% of tokens used by comparable methods. This study presents an efficient, training-free paradigm for RAG enhancement that effectively optimizes retrieval quality while maintaining high recall. Our code is released at https://github.com/BUPT-Reasoning-Lab/NeocorRAG.

Shiyao Peng, Qianhe Zheng, Zhuodi Hao +7

Beijing University of Posts and Telecommunications

Multi-Hop QARetrieval-Augmented GenerationRAG EvaluationEvidence Retrieval
AskPDF
Apr 30, 2026

EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory

Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine queries via generated content or document-level signals, but none explicitly diagnoses the evidence gap, namely what is missing from the accumulated retrieval set, leaving query refinement untargeted. We present EviMem, combining IRIS (Iterative Retrieval via Insufficiency Signals), a closed-loop framework that detects evidence gaps through sufficiency evaluation, diagnoses what is missing, and drives targeted query refinement, with LaceMem (Layered Architecture for Conversational Evidence Memory), a coarse-to-fine memory hierarchy supporting fine-grained gap diagnosis. On LoCoMo, EviMem improves Judge Accuracy over MIRIX on temporal (73.3% to 81.6%) and multi-hop (65.9% to 85.2%) questions at 4.5x lower latency. Code: https://github.com/AIGeeksGroup/EviMem.

Yuyang Li, Yime He, Zeyu Zhang +1

The Australian National University · UNSW Sydney

Temporal IREvidence RetrievalPersistent Memory for Language ModelsMulti-Hop QAInformation RetrievalLong-Term Conversational Memory+1
AskPDF
Apr 27, 2026

SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering

Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reasoning paths in response to the complex user queries, and accurately retrieving essential knowledge in the face of potential limitations in large language models (LLMs). Existing approaches primarily rely on prompt-based methods to generate reasoning paths, which are further combined with traditional sparse or dense retrieval to produce the final answer. However, the generation of reasoning paths commonly lacks effective control over the generative process, thus leading the reasoning astray. Meanwhile, the retrieval methods over-rely on knowledge matching or similarity scores rather than evaluating the practical utility of the information, resulting in retrieving homogeneous or non-useful information. Therefore, we propose a Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator framework named SEARCH-R. Specifically, SEARCH-R trains an end-to-end reasoning path navigator, which is able to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model. Moreover, a novel dependency tree-based retrieval is designed to evaluate the informational contribution of the document quantitatively. Extensive experiments on three challenging multi-hop datasets validate the effectiveness of the proposed framework. The code and dataset are available at: https://github.com/Applied-Machine-Learning-Lab/ACL2026_SEARCH-R.

Yuqing Fu, Yimin Deng, Wanyu Wang +9

City University of Hong Kong · Xi’an Jiaotong University · Michigan State University +2

Multi-Hop QAQuestion DecompositionInformation RetrievalMulti-Hop Reasoning
AskPDF
Apr 26, 2026

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA

Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is adequate. In practice, systems may answer from incomplete evidence chains, or they may accumulate redundant or distractor-heavy text that interferes with later retrieval and reasoning. We propose S2G-RAG (Structured Sufficiency and Gap-judging RAG), an iterative framework with an explicit controller, S2G-Judge. 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. These gap items are then mapped into the next retrieval query, producing stable multi-turn retrieval trajectories. To reduce noise accumulation, S2G-RAG maintains a sentence-level Evidence Context by extracting a compact set of relevant sentences from retrieved documents. Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval. Furthermore, S2G-RAG can be integrated into existing RAG pipelines as a lightweight component, without modifying the search engine or retraining the generator.

Minghan Li, Junjie Zou, Xinxuan Lv +2

Soochow University, Suzhou, China

Multi-Hop QARetrieval-Augmented GenerationIterative RAG
AskPDF
Apr 23, 2026

StructMem: Structured Memory for Long-Horizon Behavior in LLMs

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose StructMem, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on LoCoMo, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem .

Buqiang Xu, Yijun Chen, Jizhan Fang +5

Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group

Multi-Hop QATemporal ReasoningPersistent Memory for Language ModelsHierarchical MemoryLong-Term Conversational Memory
AskPDF
Apr 21, 2026

Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees

Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles with, enabling multi-hop reasoning. Yet most existing graph-based methods suffer from (i) heuristic designs lacking theoretical guarantees for subgraph quality or relevance and/or (ii) the use of static exploration strategies that ignore the query's holistic meaning, retrieving neighborhoods or communities regardless of intent. We propose Query-Aware Flow Diffusion RAG (QAFD-RAG), a training-free framework that dynamically adapts graph traversal to each query's holistic semantics. The central innovation is query-aware traversal: during graph exploration, edges are dynamically weighted by how well their endpoints align with the query's embedding, guiding flow along semantically relevant paths while avoiding structurally connected but irrelevant regions. These query-specific reasoning subgraphs enable the first statistical guarantees for query-aware graph retrieval, showing that QAFD-RAG recovers relevant subgraphs with high probability under mild signal-to-noise conditions. The algorithm converges exponentially fast, with complexity scaling with the retrieved subgraph size rather than the full graph. Experiments on question answering and text-to-SQL tasks demonstrate consistent improvements over state-of-the-art graph-based RAG methods.

Zhuoping Zhou, Davoud Ataee Tarzanagh, Sima Didari +7

Samsung SDS Research America, Mountain View, CA, USA

Multi-Hop QAGraph Retrieval-Augmented GenerationGraph-Based RetrievalGraph Diffusion
AskPDF
Apr 20, 2026

Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge to answer questions more accurately. However, research on evaluating RAG systems-particularly the retriever component-remains limited, as most existing work focuses on single-context retrieval rather than multi-hop queries, where individual contexts may appear irrelevant in isolation but are essential when combined. In this research, we use the HotPotQA, MuSiQue, and SQuAD datasets to simulate a RAG system and compare three LLM-as-judge evaluation strategies, including our proposed Context-Aware Retriever Evaluation (CARE). Our goal is to better understand how multi-hop reasoning can be most effectively evaluated in RAG systems. Experiments with LLMs from OpenAI, Meta, and Google demonstrate that CARE consistently outperforms existing methods for evaluating multi-hop reasoning in RAG systems. The performance gains are most pronounced in models with larger parameter counts and longer context windows, while single-hop queries show minimal sensitivity to context-aware evaluation. Overall, the results highlight the critical role of context-aware evaluation in improving the reliability and accuracy of retrieval-augmented generation systems, particularly in complex query scenarios. To ensure reproducibility, we provide the complete data of our experiments at https://github.com/lorenzbrehme/CARE.

Lorenz Brehme, Thomas Ströhle, Ruth Breu

Universität Innsbruck, Technikerstraße 21a, 6020 Innsbruck, Austria

Multi-Hop QALLM-as-a-JudgeRAG EvaluationIR Evaluation
AskPDF
Apr 19, 2026

STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering

Multi-hop question answering (MHQA) enables accurate answers to complex queries by retrieving and reasoning over evidence dispersed across multiple documents. Existing MHQA approaches mainly rely on iterative retrieval-augmented generation, which suffer from the following two major issues. 1) Existing methods prematurely commit to surface-level entities rather than underlying reasoning structures, making question decomposition highly vulnerable to lexical ambiguity. 2) Existing methods overlook the logical dependencies among reasoning steps, resulting in uncoordinated execution. To address these issues, we propose STRIDE, a framework that separates strategic planning, dynamic control, and grounded execution. At its core, a Meta-Planner first constructs an entity-agnostic reasoning skeleton to capture the abstract logic of the query, thereby deferring entity grounding until after the reasoning structure is established, which mitigates disambiguation errors caused by premature lexical commitment. A Supervisor then orchestrates sub-question execution in a dependency-aware manner, enabling efficient parallelization where possible and sequential coordination when necessary. By dynamically deciding whether to retrieve new evidence or infer from existing facts, it avoids redundant queries and error propagation, while fusing cross-branch information and reformulating failed queries to enhance robustness. Grounded fact extraction and logical inference are delegated to specialized execution modules, ensuring faithfulness through explicit separation of retrieval and reasoning. We further propose STRIDE-FT, a modular fine-tuning framework that uses self-generated execution trajectories from STRIDE, requiring neither human annotations nor stronger teacher models. Experiments show that STRIDE achieves robust and accurate reasoning, while STRIDE-FT effectively enhances open-source LLMs.

Wei Chen, Lili Zhao, Zhi Zheng +2

University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence Hefei, Anhui, China · NIO Hefei, Anhui, China

Multi-Hop QASelf-Training for Language ModelsQuestion DecompositionQuestion AnsweringAgentic RAGMulti-Hop Reasoning
AskPDF
Apr 18, 2026

RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence

When does an LLM controller outperform rule-based traversal for knowledge graph exploration? We study this question through RLM-on-KG, a retrieval system that treats an LLM as an autonomous navigator over an RDF-encoded mention graph for grounded question answering. Unlike GraphRAG pipelines that rely on offline LLM indexing, RLM-on-KG performs entity-first, multi-hop exploration at query time using deterministic graph construction and a fixed tool set. Our central finding is a conditional advantage: the value of LLM control depends on evidence scatter and tool-calling sophistication. The paper's core claim is LLM control versus heuristic traversal, not a generic win over GraphRAG. On GraphRAG-Bench Novel (519 questions), Gemini 2.0 Flash achieves +2.47 pp F1 over a rule-based heuristic baseline (p < 0.0001), but only +0.16 pp over a GraphRAG-local variant (not significant). With a stronger controller, Claude Haiku 4.5, the gain over heuristic grows to +4.37 pp (p < 0.001) and extends to a +2.42 pp significant improvement over GraphRAG-local (p < 0.001). The gain is largest when gold evidence is scattered across 6-10 chunks (+3.21 pp) and smallest for concentrated evidence (+1.85 pp). Cross-scale validation on MuSiQue confirms that the LLM-over-heuristic advantage transfers, with expected attenuation on smaller per-question graphs. The core architectural insight is the separation of candidate discovery from ranking: the LLM adds value through exploration breadth, while final evidence selection is best handled by pure vector re-ranking. Beyond retrieval, exploration traces provide a proposed stress-test harness for structured data quality, yielding diagnostics for coverage, connectivity, provenance, and queryability.

Andrea Volpini, Elie Raad

WordLift

Multi-Hop QALLM Reasoning with GraphsGraph Retrieval-Augmented GenerationGraph-Based RetrievalKnowledge Graph Question Answering
AskPDF
Apr 15, 2026

TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation

Retrieval-augmented generation systems struggle with temporal reasoning and evidence fusion when answering complex questions over historical criminal case narratives. Existing approaches either retrieve independently of query semantics or fail to integrate multiple evidence sources coherently. We propose Temporal Context Augmented Retrieval Generation (TCAR-Gen), a framework that combines query-conditioned graph neural networks, temporal evidence fusion, and chain-of-trees reasoning to ground answer generation in retrieved evidence. On the Victorian Crime Diaries benchmark, TCAR-Gen achieves 0.3738 Recall@5, outperforming Vanilla RAG, Temporal RAG, GraphRAG-C, and GraphRAG-T across seven query types including multi-hop reasoning and counterfactual questions. Ablation studies reveal that the context graph, temporal penalty mechanism, and query conditioning are critical components. Cross-model evaluation across five language model (GPT-OSS 20B to TinyLlama 1.1B) demonstrates that TCAR-Gen maintains robust retrieval coverage at smaller model scales, though generation quality degrades substantially with reduced model capacity. Our work shows that explicit temporal modelling and multi-branch evidence fusion are essential for faithful, reasoning-intensive question answering over knowledge-grounded corpora.

Sidra Nasir, Muhammad Noman Zahid, Rizwan Ahmed Khan

Dipartimento di Informatica, Università di Verona, Italy · School of Advanced Studies, University of Camerino, Italy · Department of Computer Science, School of Mathematics and Computer Science, Institute of Business Administration (IBA), Karachi, Pakistan

Graph Retrieval-Augmented GenerationTemporal QAGraph-Based RetrievalMulti-Hop QA
AskPDF
Apr 14, 2026

Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting

Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question Answering (KBQA) mitigates this by grounding generation in Knowledge Graphs (KGs). However, most multi-hop KBQA methods rely on explicit edge traversal, making them fragile to KG incompleteness. In this paper, we proposed a novel graph-based soft prompting framework that shifts the reasoning paradigm from node-level path traversal to subgraph-level reasoning. Specifically, we employ a Graph Neural Network (GNN) to encode extracted structural subgraphs into soft prompts, enabling LLM to reason over richer structural context and identify relevant entities beyond immediate graph neighbors, thereby reducing sensitivity to missing edges. Furthermore, we introduce a two-stage paradigm that reduces computational cost while preserving good performance: a lightweight LLM first leverages the soft prompts to identify question-relevant entities and relations, followed by a more powerful LLM for evidence-aware answer generation. Experiments on four multi-hop KBQA benchmarks show that our approach achieves state-of-the-art performance on three of them, demonstrating its effectiveness. Code is available at the repository: https://github.com/Wangshuaiia/GraSP.

Shuai Wang, Xixi Wang, Yinan Yu

Chalmers University of Technology and University of Gothenburg, Sweden · Technical University of Denmark, Kgs. Lyngby, Denmark

Knowledge Graph Question AnsweringMulti-Hop QALLM Reasoning with GraphsKnowledge Graphs
AskPDF
Apr 14, 2026

Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents

This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We propose Agentic Knowledge Graphs featuring Recursive Crawling as a robust solution for navigating superseding logic and multi-hop references. Our benchmark evaluation using the Code of Federal Regulations (CFR) demonstrates that this Knowledge Graph-enhanced approach achieves a 70% accuracy improvement over standard vector-based RAG systems, providing exhaustive and precise answers for complex regulatory queries.

Koushik Chakraborty, Koyel Guha

Google AI, Global Services Delivery

Graph Retrieval-Augmented GenerationKG ConstructionAgentic RetrievalMulti-Hop QA
AskPDF
Apr 13, 2026

DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking

Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental challenge lies in efficiently identifying the minimal relevant document set from retrieved candidates while maintaining high recall. We present an efficient dual-view cascaded reranking framework for multi-hop document reranking. Operating as a lightweight post-retrieval stage over E5-base-v2 candidates, our architecture comprises: (1) a Local Scorer employing stacked cross-attention for fine-grained query-document relevance; and (2) a Global Scorer modeling inter-document dependencies via Transformer-based context aggregation. These views are dynamically fused through an Adaptive Gate conditioned on query semantics. Under the fixed candidate set reranking setting with offline cached embeddings, our model achieves competitive results, particularly outstanding on MuSiQue with 99.4% Top-4 Recall and 97.8% Full Hit accuracy at 4.0 ms latency (249 QPS). It substantially outperforms 600M-parameter cross-encoders (BGE-Large: 92.0% Recall, Jina-v3: 90.1% Recall) while maintaining 5 to 6 times lower latency. Ablation studies validate that both Local and Global views contribute substantially to multi-hop performance.

Litong Zhang, Jiaxin Li, Kuo Zhao

Jinan University, Guangzhou, Guangdong, China

Multi-Hop QALearning to RankCross-Encoder Reranking
AskPDF
Apr 13, 2026

TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering

Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration. To address these challenges, we propose Trajectoryaware Reasoning with Adaptive Context and Exploration priors (TRACE), an experiential framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance the coherence and robustness of multihop KGQA. Specifically, TRACE dynamically translates evolving reasoning paths into natural language narratives to maintain semantic continuity, while abstracting prior exploration trajectories into reusable experiential priors that capture recurring exploration patterns. A dualfeedback re-ranking mechanism further integrates contextual narratives with exploration priors to guide relation selection during reasoning. Extensive experiments on multiple KGQA benchmarks demonstrate that TRACE consistently outperforms state-of-the-art baselines.

Yingxu Wang, Jiaxin Huang, Mengzhu Wang +1

Mohamed bin Zayed University of Artificial Intelligence · Hebei University of Technology · City University of Hong Kong

Knowledge Graph Question AnsweringMulti-Hop QALLM Reasoning with Graphs
AskPDF
Apr 13, 2026

Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds

This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation framework integrating two external benchmarks (DocRED, HotpotQA), WebQuestionsSP-style synthetic data, and the RAGAS evaluation framework in an automated pipeline. On 500 document-level relations, our system achieves an F1 of 0.70 ±\pm 0.041 in zero-shot, compared to 0.80 for supervised DREEAM. Text-to-query achieves an accuracy of 0.80 ±\pm 0.06 on 200 samples. Multi-hop reasoning achieves an Exact Match (EM) of 0.46±\pm0.04 on 500 HotpotQA questions, with a RAGAS faithfulness of 0.96 ±\pm 0.04 on 50 samples. Beyond the pipeline, we study diversity mechanisms for difficult multi-hop reasoning. On 181 questions unsolvable at zero temperature, self-consistency (k=5, T =0.7) recovers up to 23% EM with a single Mixture-of-Experts (MoE) model, but the cross-model oracle (3 architectures x 5 samples) reaches 46.4%. We highlight an agreement paradox: strong consensus among samples signals collective hallucination rather than a reliable answer, echoing the work of Moussa{ï}d et al. on the wisdom of crowds. Extending to the full pipeline (500 questions), self-consistency (k=3) raises EM from 0.46 to 0.48 ±\pm 0.04. A confidence-routing cascade mechanism (Phi-4 →\rightarrow GPT-OSS, k=5) achieves an EM of 0.55 ±\pm 0.04, the best result obtained, with 45.4% of questions rerouted. Finally, we show that V3 prompt engineering applied to other models does not reproduce the gains observed with Gemma-4, confirming the specific prompt/model interaction. The entire system runs in ∼\sim5 h on a single RTX 3090, without any training, for an estimated carbon footprint of 0.09 kg CO2 eq.

Pierre Jourlin

LIA · Avignon Université, Laboratoire d’Informatique d’Avignon (LIA)

KG ConstructionKnowledge Graph Question AnsweringMulti-Hop QALanguage Model EnsemblesSelf-Consistency in Language ModelsHallucination in Language Models
AskPDF
Apr 11, 2026

STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation

To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook the inherent challenge of sparse semantic information in graphs. Specifically, our experiments reveal that these methods produce biased retrieval Semantic Shortcut Bias and Long-Tail Path Bias, leading to inadequate semantic modeling and limited GraphRAG effectiveness. To address these issues, we propose STAR, a semantic-tuned and tail-adaptive retriever for GraphRAG. STAR integrates two key learning paradigms: token-level interaction learning and path-weighted contrastive learning. The former employs a cross-attention architecture and a hard path mining mechanism to jointly model the query and path, thereby mitigating the Semantic Shortcut Bias. The latter introduces a tailored contrastive learning objective that utilizes tail-adaptive path weighting, designed to optimize the training process and ease the Long-Tail Path Bias. Extensive experiments demonstrate that STAR consistently outperforms baselines, achieving average retrieval performance gains of 1.8% and LLM QA performance improvements of 2.2% across all benchmark datasets. Our code is available at https://anonymous.4open.science/r/STAR-C583.

Shuai Li, Chen Huang, Duanyu Feng +2

Graph Retrieval-Augmented GenerationKnowledge Graph Question AnsweringMulti-Hop QAContrastive Learning
AskPDF
Apr 10, 2026

Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA

Two-hop QA retrieval splits queries into two regimes determined by whether the hop-2 entity is explicitly named in the question (Q-dominant) or only in the bridge passage (B-dominant). We formalize this split with three theorems: (T1) per-query AUC is a monotone function of the cosine separation margin, with R^2 >= 0.90 for six of eight type-encoder pairs; (T2) regime is characterized by two surface-text predicates, with P1 decisive for routing and P2 qualifying the B-dominant case, holding across three encoders and three datasets; and (T3) bridge advantage requires the relation-bearing sentence, not entity name alone, with removal causing an 8.6-14.1 pp performance drop (p < 0.001). Building on this theory, we propose RegimeRouter, a lightweight binary router that selects between question-only and question-plus-relation-sentence retrieval using five text features derived directly from the predicate definitions. Trained on 2WikiMultiHopQA (n = 881, 5-fold cross-fitted) and applied zero-shot to MuSiQue and HotpotQA, RegimeRouter achieves +5.6 pp (p < 0.001), +5.3 pp (p = 0.002), and +1.1 pp (non-significant, no-regret) R@5 improvement, respectively, with artifact-driven.

Andre Bacellar

Multi-Hop RetrievalMulti-Hop QAInformation RetrievalAdaptive Retrieval
AskPDF
Apr 8, 2026

SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or predetermined reasoning path, they remain challenging. Recent approaches train models using reinforcement learning on the model's outcome, showing promise in improving how models handle complex information. We introduce SubSearch, a specialized framework that shifts from outcome-only supervision to intermediate reward signals that incentivize planning high-quality reasoning. Unlike previous work on process reward modeling, which focuses on training a separate reward model with annotated trajectories by either human annotators or large LLM judges, SubSearch directly optimizes the generator using intrinsic process rewards, which we define as internally-derived rewards, eliminating the need for external supervision, and moving towards autonomous information-intensive reasoning. Experiments on seven benchmarks show that rewarding intermediate reasoning steps with intrinsic rewards leads to more robust reasoning traces in both QA and multi-hop QA datasets over using only outcome rewards. SubSearch can help in building reasoning traces that allow agents to better integrate search engines for complex query answering, while offering a data-efficient alternative to supervised process modeling.

Roxana Petcu, Evangelos Kanoulas, Maarten de Rijke

IRLab, University of Amsterdam

RL for Language Model ReasoningProcess Reward ModelsRL for IRMulti-Hop QARetrieval-Augmented Generation
AskPDF
Apr 8, 2026

DTCRS: Dynamic Tree Construction for Recursive Summarization

Retrieval-Augmented Generation (RAG) mitigates the hallucination problem of Large Language Models (LLMs) by incorporating external knowledge. Recursive summarization constructs a hierarchical summary tree by clustering text chunks, integrating information from multiple parts of a document to provide evidence for abstractive questions involving multi-step reasoning. However, summary trees often contain a large number of redundant summary nodes, which not only increase construction time but may also negatively impact question answering. Moreover, recursive summarization is not suitable for all types of questions. We introduce DTCRS, a method that dynamically generates summary trees based on document structure and query semantics. DTCRS determines whether a summary tree is necessary by analyzing the question type. It then decomposes the question and uses the embeddings of sub-questions as initial cluster centers, reducing redundant summaries while improving the relevance between summaries and the question. Our approach significantly reduces summary tree construction time and achieves substantial improvements across three QA tasks. Additionally, we investigate the applicability of recursive summarization to different question types, providing valuable insights for future research.

Guanran Luo, Zhongquan Jian, Wentao Qiu +2

School of Informatics, Xiamen University

Text SummarizationMulti-Hop QARetrieval-Augmented Generation
AskPDF