Metraipolis › archive › dc_e522c98b699a
Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG — arXiv:2610.21184
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21184
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:55:49.778Z
- SHA-256 of the archived text
c14616d1102d6583bd23dc05612a4d91ac0e35e357b45220ba003f9765cdc7b0- Stable URL of this page
https://metraipolis.com/documento/dc_e522c98b699a
How to cite
Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG — arXiv:2610.21184 — arXiv (en), https://arxiv.org/abs/2610.21184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e522c98b699a (Metraipolis archive dc_e522c98b699a, sha256 c14616d1102d6583bd23dc05612a4d91ac0e35e357b45220ba003f9765cdc7b0)
BibTeX
@misc{dce522c98b699a,
title = {Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG — arXiv:2610.21184},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21184},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e522c98b699a; sha256 c14616d1102d6583bd23dc05612a4d91ac0e35e357b45220ba003f9765cdc7b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions. When a wrong answer lacks a required passage, the passage may be inaccessible to the retriever, or the agent may have failed to issue a query that would retrieve it. Standard retrieval evaluations conflate these two causes. We study how much apparent retrieval failure is instead caused by search drift: the search no longer tracks an unanswered sub-question. Holding the retriever, corpus, and generation model fixed, we introduce ExecutionRAG, a training-free requirement register that records open sub-questions and their supporting evidence. The register changes search guidance but not evidence access, so each gold passage it recovers certifies that the passage was reachable by the original retriever. On 1,000 MuSiQue questions, the number of wrong answers with unretrieved required evidence falls from 382 to 234 with all-MiniLM-L6-v2 and from 383 to 274 with Qwen3-Embedding-0.6B. These counts correspond to 69% to 44% and 66% to 48% of each system's wrong answers, respectively. Crucially, evidence recovery does not produce a proportional reduction in total error: premature resolutions and abstentions increase as missing-evidence failures decrease. The central finding is therefore a shift in the remaining bottleneck, from guiding search toward required evidence to verifying that the retrieved evidence is sufficient. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.21184 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:47.630Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).