phenomenon · first seen 7 Oct 2026
multi-hop reasoning
Also: multi-hop QA, multi-hop question answering
Answering questions requiring chaining several inference steps, studied here in multilingual language models.
Mentions per week
PapersCodeDiscussion
Rank 196 on 1 Nov 2026 · 9 mentions in 28 days · 9 independent groups · papers · first seen 4 weeks ago · acceleration -0.12
Earliest sources
- Bridge Routing Heads: Where Multilingual Multi-hop Reasoning Lives in LLMsPapers · 7 Oct 2026 · Seunghan Kim, Minyeong Choe, Hyunil Kim, Haehyun Cho
- RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented GenerationPapers · 14 Oct 2026 · Linyao Zheng, Xuhang Shi, Zhifang Mao, Xiuquan Hou, Sai Zhou
- FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise EvaluationPapers · 19 Oct 2026 · Yuxuan Wu, Miaopei Lin, Qiufang Ying, Lin Dan, Hao Zhao, Qirui Liu, Yuteng Shen,…
- RESIN: Multi-Chain Reasoning with Entity-Structured IndexingPapers · 19 Oct 2026 · Xuanyu Meng, Jash Rajesh Parekh, Jiawei Han
- Collective Emergent Alignment: Measuring and Amplifying Interaction-Induced Reasoning Alignment in Multi-Agent LLMsPapers · 26 Oct 2026 · Boxuan Wang, Zhuoyun Li, Sarvapali D. Ramchurn, Xiaowei Huang, Yi Dong
- SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented GenerationPapers · 27 Oct 2026 · Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazan…
Latest sources
- DetouR: Plugging Association Routes into Search Agents for Multi-hop Question AnsweringPapers · 15 Nov 2026 · Tingwei Chen, Yunxiao Shi, Zhendong Chu, Zhiying Deng, Min Xu, Qingsong Wen
- ChainCheck: Near-Perfect Evidence-Sufficiency Scores Can Conceal Sensitivity to Construction Artifacts -- Paired Conditional Contrasts that Expose an Evaluation ConfoundPapers · 9 Nov 2026 · Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon
- FondueQA: A Benchmark for Evaluating Parametric Compensation in Multi-Hop QAPapers · 6 Nov 2026 · Laurin Schmid, Suman Navaratnarajah, Koel Dutta Chowdhury, Steffen Eger, Josif G…
- Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination MitigationPapers · 5 Nov 2026 · Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani
- Where Search Agents Go Off the Rails: Graph-Grounded Step-Level VerificationPapers · 4 Nov 2026 · Hyeseo Jeon, Seonho Yoo, Jay-Yoon Lee
- EAGR: Evidence-Guided Adaptive Graph RetrievalPapers · 1 Nov 2026 · Sonam Gupta, Vignesh P, Vishwajeet Kumar, Adnan Qidwai, Anand Eswaran, Jaydeep S…
- ImplicitHop: Evaluating knowledge integration across context and memoryPapers · 30 Oct 2026 · Alexander Detkov, Dashiel Karish, Matthew Oleynikov, Matt Thomson
- DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable AnswersPapers · 27 Oct 2026 · Dingyi Kang, Bingzhe Li
- SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented GenerationPapers · 27 Oct 2026 · Zafer Sahinoglu, Abdulazeez Mohammed, Buse Yaren Kazangirler, Cahit Berkay Kazan…
- Collective Emergent Alignment: Measuring and Amplifying Interaction-Induced Reasoning Alignment in Multi-Agent LLMsPapers · 26 Oct 2026 · Boxuan Wang, Zhuoyun Li, Sarvapali D. Ramchurn, Xiaowei Huang, Yi Dong
- RESIN: Multi-Chain Reasoning with Entity-Structured IndexingPapers · 19 Oct 2026 · Xuanyu Meng, Jash Rajesh Parekh, Jiawei Han
- FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise EvaluationPapers · 19 Oct 2026 · Yuxuan Wu, Miaopei Lin, Qiufang Ying, Lin Dan, Hao Zhao, Qirui Liu, Yuteng Shen,…