Metraipolis › archive › dc_bfbb89509f99

CAVE-Mem: Boundary-Aware Experience Validation for Memory Search — arXiv:2610.00238

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00238
License (as archived): CC0-1.0
Archived: 2026-10-06T12:08:14.301Z
SHA-256 of the archived text: 58249c298698e2ac30b6874fa9ac7ee99a051fe3021fbe0a9163c29b7891d869
Stable URL of this page: https://metraipolis.com/documento/dc_bfbb89509f99

How to cite

CAVE-Mem: Boundary-Aware Experience Validation for Memory Search — arXiv:2610.00238 — arXiv (en), https://arxiv.org/abs/2610.00238 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bfbb89509f99 (Metraipolis archive dc_bfbb89509f99, sha256 58249c298698e2ac30b6874fa9ac7ee99a051fe3021fbe0a9163c29b7891d869)

BibTeX

@misc{dcbfbb89509f99,
  title = {CAVE-Mem: Boundary-Aware Experience Validation for Memory Search — arXiv:2610.00238},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00238},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bfbb89509f99; sha256 58249c298698e2ac30b6874fa9ac7ee99a051fe3021fbe0a9163c29b7891d869},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00238. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-term memory agents increasingly rely on it- erative search and reusable experience to answer questions over large personal, factual, or narrative histories. However, current experience-memory systems largely optimize relevance: they re- trieve past search lessons that appear similar to the current state and inject them into the prompt. A relevant experience can still be harmful when the memory substrate, question intent, answer granularity, or evidence boundary changes. We propose CAVE- Mem, a training-free framework that represents experience as a typed intervention operator with applicability, boundary, and utility conditions. CAVE-Mem first obtains a base memory-search answer, then allows an operator to change it only if the oper- ator matches the current substrate, answer contract, evidence boundary, and cross-fitted utility; otherwise the system abstains. Experiments across long-term conversational memory, multi-hop question answering, and long-document narrative reasoning show consistent gains over relevance-only experience reuse.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00238 — 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 2026-10-06T10:21:28.032Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).