Multi-Hop QA

QA: Question Answering

Follow this topic Ask about this topic

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

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

Apr 8, 2026

WRAP++: Web discoveRy Amplified Pretraining

Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. However, existing approaches operate at the single-document level, rewriting individual web pages in isolation. This confines synthesized examples to intra-document knowledge, missing cross-document relationships and leaving facts with limited associative context. We propose WRAP++ (Web discoveRy Amplified Pretraining), which amplifies the associative context of factual knowledge by discovering cross-document relationships from web hyperlinks and synthesizing joint QA over each discovered document pair. Concretely, WRAP++ discovers high-confidence relational motifs including dual-links and co-mentions, and synthesizes QA that requires reasoning across both documents. This produces relational knowledge absent from either source document alone, creating diverse entry points to the same facts. Because the number of valid entity pairs grows combinatorially, this discovery-driven synthesis also amplifies data scale far beyond single-document rewriting. Instantiating WRAP++ on Wikipedia, we amplify ~8.4B tokens of raw text into 80B tokens of cross-document QA data. On SimpleQA, OLMo-based models at both 7B and 32B scales trained with WRAP++ substantially outperform single-document approaches and exhibit sustained scaling gains, underscoring the advantage of cross-document knowledge discovery and amplification.

Jiang Zhou, Yunhao Wang, Xing Wu +2

Knowledge Augmentation for Language Models Synthetic Data Pretraining Synthetic Data Generation for Language Models Multi-Hop QA

Apr 7, 2026

MTA-Agent: An Open Recipe for Multimodal Deep Search Agents

Multimodal large language models (MLLMs) have demonstrated strong capabilities in visual understanding, yet they remain limited in complex, multi-step reasoning that requires deep searching and integrating visual evidence with external knowledge. In this work, we address this challenge by constructing high-quality, verified multi-hop vision-language training data for multimodal deep-search agents. We propose a Multi-hop Tool-Augmented Agent for Evidence-based QA Synthesis (MTA-Agent), which automatically selects tools and their parameters to retrieve and validate evidence from both visual and textual sources and generates structured multi-hop question-answer trajectories. Starting from diverse VQA seed datasets, our pipeline produces a large-scale training dataset, MTA-Vision-DeepSearch, containing 21K high-quality multi-hop examples. The data is filtered through a multi-stage verification process to ensure factual consistency and answer uniqueness. Using MTA-Vision-DeepSearch, a 32B open-source multimodal search agent achieves state-of-the-art performance, reaching an average of 54.63% across six challenging benchmarks, outperforming GPT-5 (51.86%), Gemini-2.5-Pro (50.98%), and Gemini-3-Pro (54.46%) under the same tool settings. We further show that training on our data improves both reasoning depth and tool-use behavior, increasing the average number of steps from 2.27 to 4.28, and leading to more systematic and persistent search strategies. Additionally, we demonstrate that training can be performed without real-time tool calls by replaying cached interactions, significantly reducing training cost. Importantly, we present MTA-Agent as a fully open recipe for multimodal deep search: we release the entire dataset, training trajectories, and implementation details to enable reproducibility and future research on open multimodal search agents.

Xiangyu Peng, Can Qin, An Yan +4

Salesforce AI Research

Multimodal Search Agents Multimodal QA Multimodal Reasoning Multi-Hop QA Tool Use in VLMs

Apr 6, 2026

DOTRAG: Retrieval-Time Reasoning Along Paths

Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods struggle to adapt to the query-specific logic required for complex multi-hop tasks, often accumulating irrelevant context or missing correct relational paths. We propose DotRAG, a training-free GraphRAG framework that reformulates retrieval as a reasoning process over paths. Our approach generates query-conditioned constraints that guide graph exploration, prune irrelevant regions, and iteratively discover relational paths without relying on explicit step-by-step reasoning chains. We introduce Division of Thought (DOT), an abstraction that decomposes retrieval into localized search spaces and adapts the search strategy to each query. DotRAG achieves SOTA performance on MetaQA and UltraDomain, with consistent gains on multi-hop tasks, demonstrating the effectiveness of reasoning-guided retrieval.

Larnell Moore, Naihao Deng, Rada Mihalcea +1

University of Michigan

Graph Retrieval-Augmented Generation Graph-Based Retrieval Multi-Hop QA Multi-Hop Reasoning

Apr 6, 2026

Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents

Agents equipped with search tools have emerged as effective solutions for knowledge-intensive tasks. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their high computational cost limits practical deployment for search agents. Consequently, recent work has focused on distilling agentic behaviors from LLMs into Small Language Models (SLMs). Through comprehensive evaluation on complex multi-hop reasoning tasks, we find that despite possessing less parametric knowledge, SLMs invoke search tools less frequently and are more prone to hallucinations. To address this issue, we propose \policy, a lightweight fine-tuning approach that explicitly trains SLMs to reliably retrieve and generate answers grounded in retrieved evidence. Compared to agent distillation from LLMs, our approach improves performance by 17.3 scores on Bamboogle and 15.3 scores on HotpotQA, achieving LLM-level results across benchmarks. Our further analysis reveals that adaptive search strategies in SLMs often degrade performance, highlighting the necessity of consistent search behavior for reliable reasoning.

Yizhou Liu, Qi Sun, Yulin Chen +2

University of Illinois Urbana-Champaign · New York University · Nanyang Technological University

Agentic Search Small Language Models LLM Agent Training Agentic RAG Multi-Hop QA

Apr 4, 2026

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm for search agents, yet outcome-only rewards are sparse and provide limited credit assignment for intermediate search actions. Existing process-reward methods therefore seek to densify supervision through proxy signals, external evaluators, or likelihood-based information gain. However, proxy rewards can deviate from the final outcome objective, while fixed evaluators can become stale as the search policy evolves, leading to unreliable process supervision. To address these challenges, we propose OASES, an Outcome-Aligned Search-Evaluation Supervision framework for agentic search. OASES derives outcome-aligned process rewards by evaluating how well each intermediate search state supports answering the original question. It further co-trains the search policy and the state evaluator on policy, allowing the evaluator to adapt to evolving search behavior and provide more reliable process rewards. Experiments on five multi-hop QA benchmarks show that OASES consistently outperforms strong RL baselines, with further analyses confirming the benefits of outcome-aligned process rewards and search-evaluation co-training.

Erhan Zhang, Yiqun Chen, Zechun Niu +6

Renmin University of China · University of Southern California · Xiaohongshu Inc.

Agentic Search Process Reward Models RL for IR Reinforcement Learning with Verifiable Rewards Multi-Hop QA

Apr 2, 2026

SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning

Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning. We propose SAFE, an LLM-as-verifier framework for evidence-grounded multi-hop QA. Rather than judging only the final answer after generation, SAFE verifies reasoning during generation by checking intermediate steps against the provided passages and previous reasoning trajectory. To make this process checkable, SAFE decomposes reasoning into atomic, evidence-grounded units represented with Knowledge Graph (KG) triples. At train-time, SAFE verifies benchmark supervision under KG-grounded constraints and constructs reliable verifier training data. At inference-time, an external verifier checks each generated step, identifies invalid reasoning, and provides correction feedback before errors propagate. Across three multi-hop QA benchmarks, SAFE improves accuracy by 8.8 pp on average. These results show that evidence-grounded multi-hop QA benefits from shifting LLM-based evaluation from post-hoc answer judgment to stepwise reasoning verification.

Daeyong Kwon, Soyoung Yoon, Seung-won Hwang

Seoul National University, South Korea

Multi-Hop QA LLM Answer Verification LLM Grounding

Mar 31, 2026

GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning

Graph-based retrieval-augmented generation (GraphRAG) has recently emerged as a powerful paradigm for knowledge-intensive question answering, especially for tasks that require structured evidence organization and multi-hop reasoning. However, existing GraphRAG systems are typically built in a one-size-fits-all manner, relying on a fixed retrieval framework and a single, often large and costly, generator LLM for all queries. This static design limits their ability to adapt to the complexity of varying questions and often incurs unnecessary computational cost. To fill in the gap, we propose GraphRAG-Router, a cost-efficient framework that adopts a hierarchical routing strategy to coordinate heterogeneous GraphRAGs and generator LLMs. Specifically, GraphRAG-Router is first warmed up through supervised fine-tuning and then optimized with a two-stage reinforcement learning procedure, whose second stage introduces a curriculum cost-aware reward to encourage difficulty-aware and economical generator allocation. Extensive experiments on six general-domain and multi-hop QA benchmarks show that GraphRAG-Router consistently outperforms state-of-the-art baselines, reducing the overuse of large LLMs by nearly 30% while maintaining strong generalization capability.

Dongzhe Fan, Chuanhao Ji, Zimu Wang +2

Department of Computer Science, New York University (Shanghai) · Department of Computer Science, University of Liverpool

LLM Routing Graph Retrieval-Augmented Generation Multi-Hop QA

Mar 30, 2026

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

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 coverage from 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 23.5% higher accuracy, with retrieval gains of up to 10.5% in NDCG.

Xingyu Li, Rongguang Wang, Yuying Wang +5

Oracle AI

Retrieval-Augmented Reasoning Multi-Document QA Retrieval-Augmented Generation Multi-Hop QA Multi-Hop Retrieval Iterative RAG+1

Mar 30, 2026

Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA

Graph-augmented retrieval combines dense similarity with graph-based relevance signals such as Personalized PageRank (PPR), but these scores have different distributions and are not directly comparable. We study this as a score calibration problem for heterogeneous retrieval fusion in multi-hop question answering. Our method, PhaseGraph, maps vector and graph scores to a common unit-free scale using percentile-rank normalization (PIT) before fusion, enabling stable combination without discarding magnitude information. Across MuSiQue and 2WikiMultiHopQA, calibrated fusion improves held-out last-hop retrieval on HippoRAG2-style benchmarks: LastHop@10 increases from 69.1% to 71.0% on MuSiQue (15W/5L, p=0.041, n=514) and LastHop@5 from 51.7% to 53.6% on 2WikiMultiHopQA (11W/2L, p=0.023, n=491), both on independent held-out test splits. Against the official HippoRAG 2 pipeline on 2WikiMultiHopQA, calibrated fusion is ahead at LastHop@10 (+6.3pp, p<10^-3) and behind at LastHop@5 (-8.4pp), a cutoff-dependent cross-over we report in full. A theory-driven ablation shows that percentile-based calibration is directionally more robust than min-max normalization on both tune and test splits (1W/6L, p=0.125), while Boltzmann weighting performs comparably to linear fusion after calibration (0W/3L, p=0.25). These results suggest that score commensuration is a robust design choice, and the exact post-calibration operator appears to matter less on these benchmarks.

Andre Bacellar

Hybrid Retrieval Data Fusion Graph-Based Retrieval Multi-Hop QA

Mar 27, 2026

OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models

Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex, multi-hop problems. While recent dynamic retrieval strategies offer improvements, they face two key challenges: 1) irrelevant retrieved noise can misdirect the reasoning process, and 2) processing full documents incurs prohibitive computational and latency costs. To address these issues, we propose OThink-SRR1, a framework that enhances large models with an iterative Search-Refine-Reason process trained via reinforcement learning. Its core Refine stage distills retrieved documents into concise, relevant facts before reasoning. We introduce GRPO-IR, an end-to-end reinforcement learning algorithm that rewards accurate evidence identification while penalizing excessive retrievals, thus training the model to be both focused and efficient. Experiments on four multi-hop QA benchmarks show our approach achieves superior accuracy over strong baselines while using fewer retrieval steps and tokens. This positions OThink-SRR1 as a potent foundational model for information-seeking agents.

Haijian Liang, Zenghao Niu, Junjie Wu +3

Shenzhen University · OPPO Research Institute

RL for RAG Agentic RAG Multi-Hop QA RAG Robustness RL for IR

Mar 26, 2026

OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion

Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge organization, they still have limitations in knowledge extraction precision, community report integrity, and retrieval performance. This paper proposes OMD-GraphRAG, an enhanced framework built upon open-source GraphRAG. The framework introduces three core innovations: (1) Ontology-Guided Knowledge Extraction that uses predefined Schema to guide LLMs in accurately identifying domain-specific entities and relations; (2) Multi-Dimensional Community Clustering Strategy that improves community completeness through alignment completion, attribute-based clustering, and multi-hop relationship clustering; (3) Dual-Channel Graph Retrieval Fusion that balances QA accuracy and performance through hybrid graph and community retrieval. Evaluation results on MultiHop-RAG benchmark show that OMD-GraphRAG outperforms mainstream open source solutions (e.g., LightRAG) in comprehensive F1 scores, particularly in inference and temporal queries.

Jie Wang, Honghua Huang, Xi Ge +3

Data Science & Artificial Intelligence Research Institute, China Unicom

Ontology-Guided Information Extraction Graph Retrieval-Augmented Generation Multi-Hop QA KG Construction Graph Clustering

Mar 19, 2026

DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering

Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the application scenario of retrieving across multilingual corpora and queries, leaving several open challenges. The first one involves the absence of benchmarks that assess RAG systems' capabilities under the multilingual multi-hop (MM-hop) QA setting. The second centers on the overreliance on LLMs' strong semantic understanding in English, which diminishes effectiveness in multilingual scenarios. To address these challenges, we first construct multilingual multi-hop QA benchmarks by translating English-only benchmarks into five languages, and then we propose DaPT, a novel multilingual RAG framework. DaPT generates sub-question graphs in parallel for both the source-language query and its English translation counterpart, then merges them before employing a bilingual retrieval-and-answer strategy to sequentially solve sub-questions. Our experimental results demonstrate that advanced RAG systems suffer from a significant performance imbalance in multilingual scenarios. Furthermore, our proposed method consistently yields more accurate and concise answers compared to the baselines, significantly enhancing RAG performance on this task. For instance, on the most challenging MuSiQue benchmark, DaPT achieves a relative improvement of 18.3% in average EM score over the strongest baseline.

Yilin Wang, Yuchun Fan, Jiaoyang Li +5

School of Computer Science and Engineering, Northeastern University, Shenyang, China · NiuTrans Research, Shenyang, China

Multi-Hop QA Multilingual QA Retrieval-Augmented Generation Multilingual IR

Mar 17, 2026

Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models

Evaluating the reasoning abilities of large language models (LLMs) solely from final answers can obscure failures in intermediate steps, especially in multi-hop QA benchmarks without step-level annotations. To address this gap, we introduce Omanic, an open-domain 4-hop QA benchmark designed not only to measure final-answer accuracy but also to diagnose where reasoning breaks down. Omanic contains 10,296 machine-generated training examples (OmanicSynth) and 967 expert-reviewed human-annotated evaluation examples (OmanicBench), with each evaluation question decomposed into single-hop sub-questions, intermediate answers, and structured graph topologies. Experiments with proprietary and open-source LLMs show that Omanic is challenging, while step-wise analysis reveals a later-hop bottleneck, factual knowledge floor, and error propagation along reasoning chains. Fine-tuning on OmanicSynth transfers to six reasoning and mathematics benchmarks, yielding a 7.41-point average gain and validating its effectiveness as supervision for reasoning-capability transfer. We release the data at https://huggingface.co/datasets/li-lab/Omanic and the code at https://github.com/XiaojieGu/Omanic.

Xiaojie Gu, Sherry T. Tong, Aosong Feng +8

The University of Tokyo · Yale University · Stanford University +3

LLM Evaluation Multi-Hop Reasoning Multi-Hop QA

Mar 17, 2026

IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation

Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach that shifts cross-document reasoning from online inference to offline indexing. IndexRAG identifies bridge entities shared across documents and generates bridging facts as independently retrievable units, requiring no additional training or fine-tuning. Experiments on three widely-used multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue) show that IndexRAG improves F1 over Naive RAG by 4.6 points on average, while requiring only single-pass retrieval and a single LLM call at inference time. When combined with IRCoT, IndexRAG achieves the best average performance among all evaluated methods, including graph-based baselines such as HippoRAG2 and FastGraphRAG, while relying on a flat vector index. Our code is available at https://github.com/Continuum-AI-Corp/IndexRAG .

Zhenghua Bao, Yi Shi

Continuum AI Shanghai, China · Continuum AI San Francisco, CA, USA

Multi-Hop QA Retrieval-Augmented Generation Multi-Document QA

Mar 15, 2026

LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos

Long video question answering (Long-Video QA) increasingly relies on agentic tool use to retrieve evidence from long videos. In realistic settings, this process often requires multi-hop retrieval, where agents must iteratively gather multiple discontinuous evidence clips. However, existing long-video benchmarks are largely static: they rarely enforce strict multi-hop retrieval and typically lack a standardized evidence-access interface, making it difficult to separate failures in retrieval planning from those in answer generation. To address this gap, we introduce LongVidSearch, a benchmark for evaluating agentic multi-hop evidence retrieval planning in long videos under standardized access constraints. LongVidSearch enforces retrieval necessity: a Hop-k question requires exactly k necessary evidence clips, and removing any single clip renders the question unsolvable. The benchmark contains 3,000 questions over 447 long videos (average length 26 minutes), covering four reasoning categories: State Mutation, Causal Inference, Global Summary, and Visual Tracking, with 2-hop, 3-hop, and 4-hop evidence requirements. To ensure fair and controlled evaluation, all agents interact with LongVidSearch through a unified tool interface, which fixes the retrieval backend and isolates the agent's ability to formulate queries and plan iterative retrieval. In addition to answer accuracy, we measure tool-call cost to analyze the accuracy-efficiency trade-off under identical access conditions. We evaluate VideoAgent-style QA agents with multiple backbone LLMs using three-judge majority voting. GPT-5 achieves the highest accuracy (42.43), outperforming Gemini 3 Pro (30.97) and GPT-4o (19.20), yet remaining below 50 %, highlighting the difficulty of multi-hop retrieval planning. With gold evidence clips, performance becomes near-perfect, confirming retrieval planning as the primary bottleneck.

Rongyi Yu, Chenyuan Duan, Wentao Zhang

Peking University & Zhongguancun Academy Beijing, China

AI Agent Benchmarks Multi-Hop QA Long-Video QA Video Retrieval

Mar 15, 2026

Automatic Inter-document Multi-hop Scientific QA Generation

Existing automatic scientific question generation studies mainly focus on single-document factoid QA, overlooking the inter-document reasoning crucial for scientific understanding. We present AIM-SciQA, an automated framework for generating multi-document, multi-hop scientific QA datasets. AIM-SciQA extracts single-hop QAs using large language models (LLMs) with machine reading comprehension and constructs cross-document relations based on embedding-based semantic alignment while selectively leveraging citation information. Applied to 8,211 PubMed Central papers, it produced 411,409 single-hop and 13,672 multi-hop QAs, forming the IM-SciQA dataset. Human and automatic validation confirmed high factual consistency, and experimental results demonstrate that IM-SciQA effectively differentiates reasoning capabilities across retrieval and QA stages, providing a realistic and interpretable benchmark for retrieval-augmented scientific reasoning. We further extend this framework to construct CIM-SciQA, a citation-guided variant achieving comparable performance to the Oracle setting, reinforcing the dataset's validity and generality.

Seungmin Lee, Dongha Kim, Yuni Jeon +2

Yonsei University, Seoul, Republic of Korea · OnomaAI, Seoul, Republic of Korea

Scientific QA Multi-Hop QA Biomedical QA RAG Evaluation

Mar 15, 2026

Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes

Enterprises increasingly need natural language (NL) question answering over hybrid data lakes that combine structured tables and unstructured documents. Current deployed solutions, including RAG-based systems, typically rely on brute-force retrieval from each store and post-hoc merging. Such approaches are inefficient and leaky, and more critically, they lack explicit support for multi-hop reasoning, where a query is decomposed into successive steps (hops) that may traverse back and forth between structured and unstructured sources. We present Agentic DAG-Orchestrated Transformer (A.DOT) Planner, a framework for multi-modal, multi-hop question answering, that compiles user NL queries into directed acyclic graph (DAG) execution plans spanning both structured and unstructured stores. The system decomposes queries into parallelizable sub-queries, incorporates schema-aware reasoning, and applies both structural and semantic validation before execution. The execution engine adheres to the generated DAG plan to coordinate concurrent retrieval across heterogeneous sources, route intermediate outputs to dependent sub-queries, and merge final results in strict accordance with the plan's logical dependencies. Advanced caching mechanisms, incorporating paraphrase-aware template matching, enable the system to detect equivalent queries and reuse prior DAG execution plans for rapid re-execution, while the DataOps System addresses validation feedback or execution errors. The proposed framework not only improves accuracy and latency, but also produces explicit evidence trails, enabling verification of retrieved content, tracing of data lineage, and fostering user trust in the system's outputs. On benchmark dataset, A.DOT achieves 14.8% absolute gain in correctness and 10.7% in completeness over baselines.

Kirushikesh D B, Manish Kesarwani, Nishtha Madaan +6

IBM Research, India · IBM Software, India

Multi-Hop QA Multimodal QA Hybrid IR Graph-Based Planning

Mar 14, 2026

The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA

Graph-RAG systems achieve strong multi-hop question answering by indexing documents into knowledge graphs, but strong retrieval does not guarantee strong answers. Evaluating KET-RAG, a leading Graph-RAG system, on three multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA), we find that 77% to 91% of questions have the gold answer in the retrieved context, yet accuracy is only 35% to 78%, and 73% to 84% of errors are reasoning failures. We propose two augmentations: (i) SPARQL chain-of-thought prompting, which decomposes questions into triple-pattern queries aligned with the entity-relationship context, and (ii) graph-walk compression, which compresses the context by ~60% via knowledge-graph traversal with no LLM calls. SPARQL CoT improves accuracy by +2 to +14 pp; graph-walk compression adds +6 pp on average when paired with structured prompting on smaller models. Surprisingly, we show that, with question-type routing, a fully augmented budget open-weight Llama-8B model matches or exceeds the unaugmented Llama-70B baseline on all three benchmarks at ~12x lower cost. A replication on LightRAG confirms that our augmentations transfer across Graph-RAG systems.

Yasaman Zarrinkia, Venkatesh Srinivasan, Alex Thomo

University of Victoria · Santa Clara University

Structured CoT Reasoning Graph Retrieval-Augmented Generation Multi-Hop QA LLM Reasoning with Graphs CoT Reasoning

Mar 14, 2026

APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To enhance search capabilities for complex tasks, most existing works integrate multi-round iterative retrieval with reasoning processes via end-to-end training. While these approaches improve problem-solving performance, they still face challenges in task reasoning and model training, especially ambiguous retrieval execution paths and sparse rewards in end-to-end reinforcement learning (RL), which can lead to inaccurate retrieval results and lower performance. We attribute these failures to hierarchical credit entanglement: a single final reward updates planning and execution together, so the model cannot clearly separate plan errors from retrieval errors. We propose APEX-Searcher, which uses a Refining Credit Assignment paradigm: planning is optimized by RL with a plan-level reward, while execution is learned by SFT. Extensive experiments show consistent gains in both multi-hop RAG and task planning across benchmarks.

Kun Chen, Qingchao Kong, Zhao Feifei +1

University of Chinese Academy of Sciences · MAIS, Institute of Automation, Chinese Academy of Sciences · Wenge Technology Co., Ltd

Agentic RAG RL for RAG Multi-Hop QA Step-Level Credit Assignment in RL RL for IR

Mar 12, 2026

Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs

While Large Language Models (LLMs) achieve expert-level performance on standard medical benchmarks through single-hop factual recall, they severely struggle with the complex, multi-hop diagnostic reasoning required in real-world clinical settings. A primary obstacle is "shortcut learning", where models exploit highly connected, generic hub nodes (e.g., "inflammation") in knowledge graphs to bypass authentic micro-pathological cascades. To address this, we introduce ShatterMed-QA, a bilingual benchmark of 10,558 multi-hop clinical questions designed to rigorously evaluate deep diagnostic reasoning. Our framework constructs a topology-regularized medical Knowledge Graph using a novel

k

-Shattering algorithm, which physically prunes generic hubs to explicitly sever logical shortcuts. We synthesize the evaluation vignettes by applying implicit bridge entity masking and topology-driven hard negative sampling, forcing models to navigate biologically plausible distractors without relying on superficial elimination. Comprehensive evaluations of 21 LLMs reveal massive performance degradation on our multi-hop tasks, particularly among domain-specific models. Crucially, restoring the masked evidence via Retrieval-Augmented Generation (RAG) triggers near-universal performance recovery, validating ShatterMed-QA's structural fidelity and proving its efficacy in diagnosing the fundamental reasoning deficits of current medical AI. Explore the dataset, interactive examples, and full leaderboards at our project website: https://shattermed-qa-web.vercel.app/

Xing Zi, Xinying Zhou, Jinghao Xiao +2

University of Technology Sydney, Australia

Shortcut Learning in Language Models Multi-Hop QA Medical QA Clinical Language Model Evaluation

Mar 12, 2026

Test-Time Strategies for More Efficient and Accurate Agentic RAG

Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these complexities. However, such approaches can introduce inefficiencies, including repetitive retrieval of previously processed information and challenges in contextualizing retrieved results effectively within the current generation prompt. Such issues can lead to unnecessary retrieval turns, suboptimal reasoning, inaccurate answers, and increased token consumption. In this paper, we investigate test-time modifications to the Search-R1 pipeline to mitigate these identified shortcomings. Specifically, we explore the integration of two components and their combination: a contextualization module to better integrate relevant information from retrieved documents into reasoning, and a de-duplication module that replaces previously retrieved documents with the next most relevant ones. We evaluate our approaches using the HotpotQA (Yang et al., 2018) and the Natural Questions (Kwiatkowski et al., 2019) datasets, reporting the exact match (EM) score, an LLM-as-a-Judge assessment of answer correctness, and the average number of turns. Our best-performing variant, utilizing GPT-4.1-mini for contextualization, achieves a 5.6% increase in EM score and reduces the number of turns by 10.5% compared to the Search-R1 baseline, demonstrating improved answer accuracy and retrieval efficiency.

Brian Zhang, Deepti Guntur, Zhiyang Zuo +7

University of Massachusetts Amherst · Adobe Research

Retrieval-Augmented Generation Agentic RAG Information Retrieval Multi-Hop QA

Mar 12, 2026

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering

Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks suffer from critical limitations: standard RAG's vector similarity-based coarse-grained retrieval often omits critical facts, graph-based RAG fails to efficiently integrate fragmented complex relationship networks, and both lack schema awareness, leading to inadequate cross-document evidence chain construction and inaccurate entity relationship deduction. To address these challenges, we propose DocSage, an end-to-end agentic framework that integrates dynamic schema discovery, structured information extraction, and schema-aware relational reasoning with error guarantees. DocSage operates through three core modules: (1) A schema discovery module dynamically infers query-specific minimal joinable schemas to capture essential entities and relationships; (2) An extraction module transforms unstructured text into semantically coherent relational tables, enhanced by error-aware correction mechanisms to reduce extraction errors; (3) A reasoning module performs multi-hop relational reasoning over structured tables, leveraging schema awareness to efficiently align cross-document entities and aggregate evidence. This agentic design offers three key advantages: precise fact localization via SQL-powered indexing, natural support for cross-document entity joins through relational tables, and mitigated LLM attention diffusion via structured representation. Evaluations on two MDMEQA benchmarks demonstrate that DocSage significantly outperforms state-of-the-art long-context LLMs and RAG systems, achieving more than 27% accuracy improvements respectively.

Teng Lin, Yizhang Zhu, Zhengxuan Zhang +2

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

Multi-Document QA Multi-Hop QA Knowledge-Intensive QA Agentic RAG Relational Reasoning LLM Information Extraction

Mar 11, 2026

MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries

Retrieval-Augmented Generation (RAG) over Knowledge Graphs (KGs) suffers from the fact that indexing approaches may lose important contextual nuance when text is reduced to triples, thereby degrading performance in downstream Question-Answering (QA) tasks, particularly for multi-hop QA, which requires composing answers from multiple entities, facts, or relations. We propose a domain-agnostic, KG-based QA framework that covers both the indexing and retrieval/inference phases. A new indexing approach called Map-Disambiguate-Enrich-Reduce (MDER) generates context-derived triple descriptions and subsequently integrates them with entity-level summaries, thus avoiding the need for explicit traversal of edges in the graph during the QA retrieval phase. Complementing this, we introduce Decompose-Resolve (DR), a retrieval mechanism that decomposes user queries into resolvable triples and grounds them in the KG via iterative reasoning. Together, MDER and DR form an LLM-driven QA pipeline that is robust to sparse, incomplete, and complex relational data. Experiments show that on standard and domain specific benchmarks, MDER-DR achieves substantial improvements over standard RAG baselines (up to 66%), while maintaining cross-lingual robustness. Our code is available at https://github.com/DataSciencePolimi/MDER-DR_RAG.

Riccardo Campi, Nicolò Oreste Pinciroli Vago, Mathyas Giudici +2

Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.

Multi-Hop QA Knowledge Graph Question Answering Graph Retrieval-Augmented Generation Question Decomposition

Mar 10, 2026

TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. However, most RAG systems still retrieve unstructured chunks and rely on one-shot generation, which often yields redundant context, low information density, and brittle multi-hop reasoning. While structured RAG pipelines can improve grounding, they typically require costly and error-prone graph construction or impose rigid entity-centric structures that do not align with the query's reasoning chain. We propose TaSR-RAG, a taxonomy-guided structured reasoning framework for evidence selection. We represent both queries and documents as relational triples, and constrain entity semantics with a lightweight two-level taxonomy to balance generalization and precision. Given a complex question, TaSR-RAG decomposes it into an ordered sequence of triple sub-queries with explicit latent variables, then performs step-wise evidence selection via hybrid triple matching that combines semantic similarity over raw triples with structural consistency over typed triples. By maintaining an explicit entity binding table across steps, TaSR-RAG resolves intermediate variables and reduces entity conflation without explicit graph construction or exhaustive search. Experiments on multiple multi-hop question answering benchmarks show that TaSR-RAG consistently outperforms strong RAG and structured-RAG baselines by up to 14%, while producing clearer evidence attribution and more faithful reasoning traces.

Jiashuo Sun, Yixuan Xie, Jimeng Shi +2

University of Illinois Urbana-Champaign

Structured RAG Retrieval-Augmented Generation Multi-Hop QA Hybrid Retrieval

Mar 10, 2026

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents

Retrieval-augmented agents can query external evidence, yet their reliability in multi-step reasoning remains limited: noisy retrieval may derail multi-hop question answering, while outcome-only reinforcement learning provides credit signals that are too coarse to optimize intermediate steps. We propose EvalAct (Evaluate-as-Action), which converts implicit retrieval quality assessment into an explicit action and enforces a coupled Search-to-Evaluate protocol so that each retrieval is immediately followed by a structured evaluation score, yielding process signals aligned with the interaction trajectory. To leverage these signals, we introduce Process-Calibrated Advantage Rescaling (PCAR), a GRPO-based optimization method that rescales advantages at the segment level according to evaluation scores, emphasizing reliable segments while updating uncertain ones conservatively. Experiments on seven open-domain QA benchmarks show that EvalAct achieves the best average accuracy, with the largest gains on multi-hop tasks, and ablations verify that the explicit evaluation loop drives the primary improvements while PCAR provides consistent additional benefits.

Jiangming Shu, Yuxiang Zhang, Ye Ma +2

School of Computer Science and Technology, Beijing Jiaotong University · Hithink Research

Retrieval-Augmented Reasoning Agentic RAG RL for LLM Agents Process Reward Models Multi-Hop QA Generative AI Evaluation

Mar 9, 2026

Gradually Excavating External Knowledge for Implicit Complex Question Answering

Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the ultimate solution due to the reasons of: 1) uncovered or out-of-date domain knowledge, 2) one-shot generation and hence restricted comprehensiveness. To this end, this work proposes a gradual knowledge excavation framework for open-domain complex question answering, where LLMs iteratively and actively acquire external information, and then reason based on acquired historical knowledge. Specifically, during each step of the solving process, the model selects an action to execute, such as querying external knowledge or performing a single logical reasoning step, to gradually progress toward a final answer. Our method can effectively leverage plug-and-play external knowledge and dynamically adjust the strategy for solving complex questions. Evaluated on the StrategyQA dataset, our method achieves 78.17% accuracy with less than 6% parameters of its competitors, setting new SOTA for ~10B-scale LLMs.

Chang Liu, Xiaoguang Li, Lifeng Shang +4

The University of Hong Kong · Huawei Noah’s Ark Lab

Iterative RAG Question Answering Knowledge Augmentation for Language Models Multi-Hop QA Retrieval-Augmented Generation

Mar 9, 2026

BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence

Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal documents. We introduce BRIDGE, a benchmark for multi-hop reasoning over long scientific papers that require integrating evidence across text, tables, and figures. The dataset supports both chain-like and fan-out structures and provides explicit multi-hop reasoning annotations for step-level evaluation beyond answer accuracy. Experiments with state-of-the-art LLMs and multimodal retrieval-augmented generation (RAG) systems reveal systematic deficiencies in evidence aggregation and grounding that remain hidden under conventional answer-only evaluation. BRIDGE provides a targeted testbed for diagnosing reasoning failures in long multimodal documents.

Biao Xiang, Soyeon Caren Han, Yihao Ding

The University of Melbourne Melbourne, Australia · The University of Western Australia Perth, Australia

Multi-Hop QA Multimodal QA Multimodal Model Evaluation Document Understanding Multimodal Grounding

Mar 6, 2026

StratRAG: A Multi-Hop Retrieval Evaluation Dataset for Retrieval-Augmented Generation Systems

We introduce StratRAG, an open-source retrieval evaluation dataset for benchmarking Retrieval-Augmented Generation (RAG) systems on multi-hop reasoning tasks under realistic, noisy document-pool conditions. Derived from HotpotQA (distractor setting), StratRAG comprises 2,200 examples across three question types -- bridge, comparison, and yes-no -- each paired with a pool of 15 candidate documents containing exactly 2 gold documents and 13 topically related distractors. We benchmark three retrieval strategies -- BM25, dense retrieval (all-MiniLM-L6-v2), and hybrid fusion -- reporting Recall@k, MRR, and NDCG@5 on the validation set. Hybrid retrieval achieves the best overall performance (Recall@2 = 0.70, MRR = 0.93), yet bridge questions remain substantially harder (Recall@2 = 0.67), motivating future work on reinforcement-learning-based retrieval policies. StratRAG is publicly available at https://huggingface.co/datasets/Aryanp088/StratRAG.

Aryan Patodiya

Department of Computer Science, California State University, Fresno, Fresno, CA, USA

Multi-Hop Retrieval RAG Evaluation Retrieval-Augmented Reasoning Information Retrieval Multi-Hop QA Hybrid Retrieval

Mar 5, 2026

S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering

We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted

k

-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a compact soft mixture of selected path latents into a language model via cross-attention. The system runs inside an iterative Neural-Socratic Graph Dialogue loop in which concise diagnostic messages produced by the language model are mapped to targeted graph edits or seed expansions, enabling adaptive retrieval when the model expresses uncertainty. This combination yields a retrieval mechanism that is both token-efficient and topology-aware while preserving interpretable path-level traces for diagnostics and intervention. We validate S-Path-RAG on standard multi-hop KGQA benchmarks and through ablations and diagnostic analyses. The results demonstrate consistent improvements in answer accuracy, evidence coverage, and end-to-end efficiency compared to strong graph- and LLM-based baselines. We further analyze trade-offs between semantic weighting, verifier filtering, and iterative updates, and report practical recommendations for deployment under constrained compute and token budgets.

Rong Fu, Yemin Wang, Tianxiang Xu +5

University of Macau · Xiamen University · Peking University +3

Knowledge Graph Question Answering Multi-Hop QA Graph Retrieval-Augmented Generation LLM Reasoning with Graphs

Mar 4, 2026

iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics

With the emergence of search-enabled generative QA systems, users are increasingly turning to tools that browse, aggregate, and reconcile evidence across multiple sources on their behalf. Yet many widely used QA benchmarks remain answerable by retrieving a single relevant passage, making them poorly suited for measuring cross-source sensemaking, such as integrating evidence, tracking causal links, and resolving dependencies across facets of a topic. We present iAgentBench, a dynamic ODQA benchmark that targets these higher-level information needs while keeping questions natural and grounded in realistic information-seeking behavior. iAgentBench draws seed topics from real-world attention signals and uses common user intent patterns to construct user-like questions whose answers require combining evidence from multiple sources, not just extracting a single snippet. Each instance is released with traceable evidence and auditable intermediate artifacts that support contamination checks and enable fine-grained diagnosis of failures in retrieval versus synthesis. Experiments across multiple LLMs show that retrieval improves accuracy, but retrieval alone does not reliably resolve these questions, underscoring the need to evaluate evidence use, not just evidence access.

Preetam Prabhu Srikar Dammu, Arnav Palkhiwala, Tanya Roosta +1

University of Washington Seattle, Washington, USA · UC Berkeley Berkeley, California, USA

AI Agent Benchmarks LLM Agent Evaluation Knowledge-Intensive QA Evidence-Grounded QA Multi-Hop QA IR Evaluation