Metraipolis › archive › dc_c7461fc2671d

From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search — arXiv:2610.07960

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07960
License (as archived)
CC0-1.0
Archived
2026-10-07T12:34:56.255Z
SHA-256 of the archived text
6c06f8f04ba61eb43cba6eadda272446b8a969bef060636ac698f050f9a1368d
Stable URL of this page
https://metraipolis.com/documento/dc_c7461fc2671d

How to cite

From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search — arXiv:2610.07960 — arXiv (en), https://arxiv.org/abs/2610.07960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7461fc2671d (Metraipolis archive dc_c7461fc2671d, sha256 6c06f8f04ba61eb43cba6eadda272446b8a969bef060636ac698f050f9a1368d)
BibTeX
@misc{dcc7461fc2671d,
  title = {From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search — arXiv:2610.07960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7461fc2671d; sha256 6c06f8f04ba61eb43cba6eadda272446b8a969bef060636ac698f050f9a1368d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in agentic search have given large language model (LLM) agents finer control over corpus exploration. However, search interfaces often return matching passages even when feedback about the candidate set would suffice for the next decision, coupling candidate refinement with source-text exposure. We propose IndexAct, an interface for Index-Native Corpus Interaction that separates candidate-set refinement from text inspection. Agents construct and manipulate persistent candidate sets through lexical conditions and set operations over an inverted index, receiving reusable state references and statistics such as candidate counts rather than matching passages. This feedback guides further refinement, while separately requested passages provide new clues or evidence that can inform subsequent operations on retained candidate sets. Experiments on five benchmarks spanning agentic search and multi-hop question answering show that IndexAct outperforms the evaluated baselines on each benchmark. On BrowseComp-Plus, it also achieves higher evidence coverage with a smaller average live context than terminal-based corpus interfaces, and maintains answer accuracy as the corpus expands. Further analyses suggest that informative refinement feedback and state reuse support continued evidence discovery, while shorter contexts or fewer search steps alone do not ensure better performance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.07960 — 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 2026-10-07T12:07:32.561Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).