Metraipolis › archive › dc_2dd81fb3b4c8

QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution — arXiv:2611.04625

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04625
License (as archived)
CC0-1.0
Archived
2026-11-04T18:36:44.630Z
SHA-256 of the archived text
49cc8e24ded213baa53e8a18750b5f8605cab3d9d0970ff120be3907b512b2c5
Stable URL of this page
https://metraipolis.com/documento/dc_2dd81fb3b4c8

How to cite

QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution — arXiv:2611.04625 — arXiv (en), https://arxiv.org/abs/2611.04625 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2dd81fb3b4c8 (Metraipolis archive dc_2dd81fb3b4c8, sha256 49cc8e24ded213baa53e8a18750b5f8605cab3d9d0970ff120be3907b512b2c5)
BibTeX
@misc{dc2dd81fb3b4c8,
  title = {QueryFlow: Multi-Hop Graph Retrieval with Adaptive Query Evolution — arXiv:2611.04625},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04625},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2dd81fb3b4c8; sha256 49cc8e24ded213baa53e8a18750b5f8605cab3d9d0970ff120be3907b512b2c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04625. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-hop retrieval-augmented generation (RAG) supports Web information seeking and fact verification by recovering complementary evidence across related pages within a limited retrieval budget. Scoring evidence independently against the original question can miss supporting units whose relevance emerges through intermediate facts. Iterative retrieval incorporates these facts into subsequent queries, while graph retrieval explicitly models relations among evidence units. Yet fixed-query graph retrievers update entity representations without adapting the query condition to accumulated relational context. We view multi-hop evidence recovery as the coupled evolution of evidence representations and query conditions, with accumulated context informing both what the retriever represents and how it searches for complementary evidence. QueryFlow realizes this perspective by recurrently integrating query-conditioned summaries of graph context into a shared query state, which controls boundary inputs and relation features for subsequent propagation. Across four representative multi-hop question answering (QA) datasets, QueryFlow achieves macro Recall@10 (R@10), Full Recall@10 (FR@10), and LLM-Acc gains of 4.98, 8.40, and 8.0 percentage points over representative baselines, respectively.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04625 — 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 2026-11-04T18:32:37.453Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).