Metraipolis › archive › dc_f2e337eeb7d6
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks — arXiv:2610.05750
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05750
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:09.290Z
- SHA-256 of the archived text
d83114a730758e8011e783acfd69f33d9bca63cddd1ed5e7478863f736962647- Stable URL of this page
https://metraipolis.com/documento/dc_f2e337eeb7d6
How to cite
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks — arXiv:2610.05750 — arXiv, https://arxiv.org/abs/2610.05750 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f2e337eeb7d6 (Metraipolis archive dc_f2e337eeb7d6, sha256 d83114a730758e8011e783acfd69f33d9bca63cddd1ed5e7478863f736962647)
BibTeX
@misc{dcf2e337eeb7d6,
title = {Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks — arXiv:2610.05750},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05750},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f2e337eeb7d6; sha256 d83114a730758e8011e783acfd69f33d9bca63cddd1ed5e7478863f736962647},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05750. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern information systems, including many agentic workflows, use dense retrieval to explore large amounts of unstructured data. However, dense retrieval relies on surface-level semantic similarity, which is insufficient for increasingly complex search applications. Here, we investigate agentic retrieval that combines the reasoning capabilities of Large Language Models (LLMs) with the efficient corpus exploration of retrievers in a ReAct agentic loop to solve complex retrieval tasks. In our experiments, we show that agentic retrieval is more effective than standard retrieval, improving nDCG@10 by 8.7 points using the same embedding model. Moreover, while specialized retrieval methods struggle on out-of-domain tasks, agentic retrieval is highly generalizable: the same pipeline achieves competitive results on both the ViDoRe v3 and BRIGHT leaderboards. However, this improvement comes at a cost. On average, agentic retrieval takes 107.4 seconds, compared to 0.67 seconds for standard retrieval, and consumes 764.1K input and 5.8K output tokens per query. In short, our study demonstrates the effectiveness of agentic retrieval in modern data systems and motivates future work on more cost-efficient retrieval agents for large-scale deployment. 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/2610.05750 — 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 2026-10-06T05:24:06.068Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).