Metraipolis › archive › dc_db176f1f5352

Group-Aware Adaptive Retrieval for Evidence Navigation — arXiv:2609.02188

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02188
License (as archived)
CC0-1.0
Archived
2026-10-17T05:46:45.238Z
SHA-256 of the archived text
1bda940380c19d9dfa06f74b9495b3907b5bb293b15e38f65bf8b22c43033ba1
Stable URL of this page
https://metraipolis.com/documento/dc_db176f1f5352

How to cite

Group-Aware Adaptive Retrieval for Evidence Navigation — arXiv:2609.02188 — arXiv (en), https://arxiv.org/abs/2609.02188 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db176f1f5352 (Metraipolis archive dc_db176f1f5352, sha256 1bda940380c19d9dfa06f74b9495b3907b5bb293b15e38f65bf8b22c43033ba1)
BibTeX
@misc{dcdb176f1f5352,
  title = {Group-Aware Adaptive Retrieval for Evidence Navigation — arXiv:2609.02188},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02188},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db176f1f5352; sha256 1bda940380c19d9dfa06f74b9495b3907b5bb293b15e38f65bf8b22c43033ba1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02188. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reasoning-intensive retrieval addresses queries whose relevance cannot be identified by surface-level matching, thereby requiring multi-step reasoning. Because relevant documents rarely appear in the initial candidate set, retrieval systems suffer from the bounded recall problem. Existing methods iteratively expand a candidate pool at the document level over a corpus graph, examining each neighbor in isolation and drifting toward a narrow region of the corpus. To address this problem, we propose Group-Aware Adaptive Retrieval for Evidence Navigation (GAREN), which explores the corpus graph through group-level expansion. GAREN organizes documents into semantically coherent and distinguishable groups based on their connections in the corpus graph. The information in each group indicates what can be accessed by expanding through it, providing guidance beyond individual document-level signals. At each iteration, GAREN uses a group-level navigator to identify promising expansion directions, retrieves documents from the selected groups, and applies a document-level reranker to evaluate the updated candidate set. Extensive experiments show that GAREN achieves up to 8.0% improvement over the strongest baseline on BRIGHT. The source code is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.02188 — 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 2026-10-17T05:23:20.838Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).