Multi-Hop Retrieval

Latest papers

16 papers5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Cross-Loop Query Handoff: How Later Loops Redirect Two-Hop Retrieval in the Ouro Looped Language Models
Oct 25, 2026Ziyu Mu, Zehua WangMulti-Hop Retrieval Multi-Hop QA
Faculty of Science The University of British Columbia · Department of Electrical and Computer Engineering The University of British Columbia
Improving the Expressive Power of Hybrid Sequence Models via Multi-Hop Retrieval
Oct 18, 2026Yam Eitan, Gilad Yehudai, Haggai MaronMulti-Hop Retrieval Hybrid Attention
Technion – Israel Institute of Technology · NVIDIA
SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
Oct 15, 2026Yuchao WuMulti-Hop Retrieval Information Retrieval
Zleap AI
T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search
Oct 5, 2026Olga Tsymboi, Ramil Latypov, Aleksandr Medvedev +5Multi-Hop QA Agentic Search
T-Tech
ConRAG: Lightweight inference of multi-hop relations
Sep 28, 2026Kilian Bänziger, Sonia Laguna, Markus Kreft +4Graph Retrieval-Augmented Generation Relational Reasoning
Agentic Systems Lab ETH Zurich · Agentic Systems Lab, ETH Zurich Norwegian University of Science and Technology
Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
Sep 18, 2026Andre BacellarMulti-Hop Retrieval Information Retrieval
HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answering
Sep 12, 2026An Nguyen Phu, Dung Nguyen Quang, Luu Hieu An +3Multi-Hop QA Factual QA
Hanoi University of Science and Technology · Monash University · University of Oregon
Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
Sep 7, 2026JungMin Yun, YoungBin KimMulti-Hop Retrieval Evidence Retrieval
Chung-Ang University Seoul, Republic of Korea
PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation
Aug 30, 2026Haokun Deng, Xunkai Li, Hongchao Qin +1Multi-Hop QA Retrieval-Augmented Generation
Department of Computer Science, Beijing Institute of Technology
EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrieval
Aug 13, 2026Xinlong Xu, Yoshua Y. LiMulti-Hop QA Graph-Based Retrieval
Nanjing University of Information Science and Technology · Meituan
Aethel: A Reproducible Graph-Retrieval Framework for Multi-Hop Financial Diligence
Jul 20, 2026Krish SapruCoreference Resolution Graph-Based Retrieval
Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
Jun 4, 2026Anuj Maharjan, Devinder Kaur, Richard MolyetRetrieval-Augmented Generation Multi-Hop Retrieval
Dept. of Electrical Engineering and Computer Science University of Toledo Toledo, OH, USA
Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA
Apr 10, 2026Andre BacellarMulti-Hop Retrieval Multi-Hop QA
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
GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
Mar 26, 2026Ruizhong Miao, Yuying Wang, Rongguang Wang +4Multi-Hop Retrieval Retrieval-Augmented Generation
Oracle AI
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

Oct 25, 2026J/K move · Enter open · S save

Cross-Loop Query Handoff: How Later Loops Redirect Two-Hop Retrieval in the Ouro Looped Language Models

Ziyu Mu, Zehua Wang

Faculty of Science The University of British Columbia · Department of Electrical and Computer Engineering The University of British Columbia

Multi-Hop Retrieval Multi-Hop QA Mechanistic Interpretability Attention Mechanisms Recursive Language Models

Open paper AskPDF arXiv

How do later loops in a pretrained looped language model repair two-hop retrieval? We study Ouro-1.4B and Ouro-2.6B by transplanting attention queries between loops at the same layer, head and final prompt position. On synthetic in-context questions, injecting the layer-indexed collection of loop-3 queries throughout loop 1 rescues 90% and 97% of questions answered incorrectly at loop 1 and correctly at loop 3, versus 24% and 21% for shuffled donors. The rescue also holds under greedy generation in Ouro-2.6B; in Ouro-1.4B it is limited to four-candidate ranking. Crossed donor-recipient swaps favor retrieval through the donor's bridge entity over copying its answer, although a substantial positional component remains in Ouro-2.6B. Late keys and values rescue far fewer targets. Freezing queries at their loop-1 values also damages two-hop accuracy more than a matched question that supplies the bridge. On natural questions, rescue is smaller and replicates only in Ouro-2.6B, and crossed swaps do not establish bridge redirection. These results identify a transferable collection of late-loop queries that supports bridge-conditioned retrieval on synthetic scenes; they do not locate where the bridge is computed or establish a single-vector handoff.