Metraipolis › archive › dc_f3d4b5779507
Retriever-Free Retrieval: Navigating Documents with Decision Models — arXiv:2610.35868
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35868
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:18.839Z
- SHA-256 of the archived text
3863f8ce14d362806c76de673cf634c86faf8a24dc392a11fdbf1a6255b07db8- Stable URL of this page
https://metraipolis.com/documento/dc_f3d4b5779507
How to cite
Retriever-Free Retrieval: Navigating Documents with Decision Models — arXiv:2610.35868 — arXiv (en), https://arxiv.org/abs/2610.35868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3d4b5779507 (Metraipolis archive dc_f3d4b5779507, sha256 3863f8ce14d362806c76de673cf634c86faf8a24dc392a11fdbf1a6255b07db8)
BibTeX
@misc{dcf3d4b5779507,
title = {Retriever-Free Retrieval: Navigating Documents with Decision Models — arXiv:2610.35868},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35868},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3d4b5779507; sha256 3863f8ce14d362806c76de673cf634c86faf8a24dc392a11fdbf1a6255b07db8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.35868 — 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 2026-10-27T07:55:30.774Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).