Multi-Hop QA

QA: Question Answering

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.

WRAP++: Web discoveRy Amplified Pretraining
Apr 8, 2026Jiang Zhou, Yunhao Wang, Xing Wu +2Knowledge Augmentation for Language Models Synthetic Data Pretraining
MTA-Agent: An Open Recipe for Multimodal Deep Search Agents
Apr 7, 2026Xiangyu Peng, Can Qin, An Yan +4Multimodal Search Agents Multimodal QA
Salesforce AI Research
DOTRAG: Retrieval-Time Reasoning Along Paths
Apr 6, 2026Larnell Moore, Naihao Deng, Rada Mihalcea +1Graph Retrieval-Augmented Generation Graph-Based Retrieval
University of Michigan
Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents
Apr 6, 2026Yizhou Liu, Qi Sun, Yulin Chen +2Agentic Search Small Language Models
University of Illinois Urbana-Champaign · New York University · Nanyang Technological University
OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
Apr 4, 2026Erhan Zhang, Yiqun Chen, Zechun Niu +6Agentic Search Process Reward Models
Renmin University of China · University of Southern California · Xiaohongshu Inc.
SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
Apr 2, 2026Daeyong Kwon, Soyoung Yoon, Seung-won HwangMulti-Hop QA LLM Answer Verification
Seoul National University, South Korea
GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
Mar 31, 2026Dongzhe Fan, Chuanhao Ji, Zimu Wang +2LLM Routing Graph Retrieval-Augmented Generation
Department of Computer Science, New York University (Shanghai) · Department of Computer Science, University of Liverpool
PAR $^2$ -RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
Mar 30, 2026Xingyu Li, Rongguang Wang, Yuying Wang +5Retrieval-Augmented Reasoning Multi-Document QA
Oracle AI
Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA
Mar 30, 2026Andre BacellarHybrid Retrieval Data Fusion
OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
Mar 27, 2026Haijian Liang, Zenghao Niu, Junjie Wu +3RL for RAG Agentic RAG
Shenzhen University · OPPO Research Institute
OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion
Mar 26, 2026Jie Wang, Honghua Huang, Xi Ge +3Ontology-Guided Information Extraction Graph Retrieval-Augmented Generation
Data Science & Artificial Intelligence Research Institute, China Unicom
DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
Mar 19, 2026Yilin Wang, Yuchun Fan, Jiaoyang Li +5Multi-Hop QA Multilingual QA
School of Computer Science and Engineering, Northeastern University, Shenyang, China · NiuTrans Research, Shenyang, China
Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
Mar 17, 2026Xiaojie Gu, Sherry T. Tong, Aosong Feng +8LLM Evaluation Multi-Hop Reasoning
The University of Tokyo · Yale University · Stanford University +3
IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation
Mar 17, 2026Zhenghua Bao, Yi ShiMulti-Hop QA Retrieval-Augmented Generation
Continuum AI Shanghai, China · Continuum AI San Francisco, CA, USA
LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos
Mar 15, 2026Rongyi Yu, Chenyuan Duan, Wentao ZhangAI Agent Benchmarks Multi-Hop QA
Peking University & Zhongguancun Academy Beijing, China
Automatic Inter-document Multi-hop Scientific QA Generation
Mar 15, 2026Seungmin Lee, Dongha Kim, Yuni Jeon +2Scientific QA Multi-Hop QA
Yonsei University, Seoul, Republic of Korea · OnomaAI, Seoul, Republic of Korea
Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes
Mar 15, 2026Kirushikesh D B, Manish Kesarwani, Nishtha Madaan +6Multi-Hop QA Multimodal QA
IBM Research, India · IBM Software, India
The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA
Mar 14, 2026Yasaman Zarrinkia, Venkatesh Srinivasan, Alex ThomoStructured CoT Reasoning Graph Retrieval-Augmented Generation
University of Victoria · Santa Clara University
APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation
Mar 14, 2026Kun Chen, Qingchao Kong, Zhao Feifei +1Agentic RAG RL for RAG
University of Chinese Academy of Sciences · MAIS, Institute of Automation, Chinese Academy of Sciences · Wenge Technology Co., Ltd
Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
Mar 12, 2026Xing Zi, Xinying Zhou, Jinghao Xiao +2Shortcut Learning in Language Models Multi-Hop QA
University of Technology Sydney, Australia
Test-Time Strategies for More Efficient and Accurate Agentic RAG
Mar 12, 2026Brian Zhang, Deepti Guntur, Zhiyang Zuo +7Retrieval-Augmented Generation Agentic RAG
University of Massachusetts Amherst · Adobe Research
DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
Mar 12, 2026Teng Lin, Yizhang Zhu, Zhengxuan Zhang +2Multi-Document QA Multi-Hop QA
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology
MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries
Mar 11, 2026Riccardo Campi, Nicolò Oreste Pinciroli Vago, Mathyas Giudici +2Multi-Hop QA Knowledge Graph Question Answering
Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation
Mar 10, 2026Jiashuo Sun, Yixuan Xie, Jimeng Shi +2Structured RAG Retrieval-Augmented Generation
University of Illinois Urbana-Champaign
Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents
Mar 10, 2026Jiangming Shu, Yuxiang Zhang, Ye Ma +2Retrieval-Augmented Reasoning Agentic RAG
School of Computer Science and Technology, Beijing Jiaotong University · Hithink Research
Gradually Excavating External Knowledge for Implicit Complex Question Answering
Mar 9, 2026Chang Liu, Xiaoguang Li, Lifeng Shang +4Iterative RAG Question Answering
The University of Hong Kong · Huawei Noah’s Ark Lab
BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence
Mar 9, 2026Biao Xiang, Soyeon Caren Han, Yihao DingMulti-Hop QA Multimodal QA
The University of Melbourne Melbourne, Australia · The University of Western Australia Perth, Australia
StratRAG: A Multi-Hop Retrieval Evaluation Dataset for Retrieval-Augmented Generation Systems
Mar 6, 2026Aryan PatodiyaMulti-Hop Retrieval RAG Evaluation
Department of Computer Science, California State University, Fresno, Fresno, CA, USA
S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering
Mar 5, 2026Rong Fu, Yemin Wang, Tianxiang Xu +5Knowledge Graph Question Answering Multi-Hop QA
University of Macau · Xiamen University · Peking University +3
iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics
Mar 4, 2026Preetam Prabhu Srikar Dammu, Arnav Palkhiwala, Tanya Roosta +1AI Agent Benchmarks LLM Agent Evaluation
University of Washington Seattle, Washington, USA · UC Berkeley Berkeley, California, USA

Apr 8, 2026J/K move · Enter open · S save

WRAP++: Web discoveRy Amplified Pretraining

Jiang Zhou, Yunhao Wang, Xing Wu, Tinghao Yu+1

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

Open paper AskPDF arXiv

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.