Metraipolis › archive › dc_2803a4b95751
Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents — arXiv:2609.02129
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02129
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T03:26:02.368Z
- SHA-256 of the archived text
046675c0791209a7c81d9e040a44ed44627d6e3245a1a3464d2ab534f475a893- Stable URL of this page
https://metraipolis.com/documento/dc_2803a4b95751
How to cite
Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents — arXiv:2609.02129 — arXiv (en), https://arxiv.org/abs/2609.02129 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2803a4b95751 (Metraipolis archive dc_2803a4b95751, sha256 046675c0791209a7c81d9e040a44ed44627d6e3245a1a3464d2ab534f475a893)
BibTeX
@misc{dc2803a4b95751,
title = {Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents — arXiv:2609.02129},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02129},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2803a4b95751; sha256 046675c0791209a7c81d9e040a44ed44627d6e3245a1a3464d2ab534f475a893},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02129. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful discovery outcomes are typically discarded rather than reused. We introduce persistent discovery context, a lightweight memory layer that stores prior intent-to-object mappings and reuses them to augment future retrieval. Across three structured data environments, persistent discovery context consistently improves retrieval quality over metadata-only search, remains effective with automatically generated memories, and exposes a reproducible interference failure mode. In lexically sparse domains, memory-only retrieval can even outperform metadata-based retrieval. These findings suggest that discovery outcomes constitute a useful form of reusable context for data-centric agents. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.02129 — 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 2026-10-17T03:13:12.423Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).