Metraipolis › archive › dc_af3db66d573f
The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory — arXiv:2610.07309
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07309
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:17:17.587Z
- SHA-256 of the archived text
1ad12b9aa81bb3dc15052a599e7187e3fe41475e4dbda342a1a74dbabaeef608- Stable URL of this page
https://metraipolis.com/documento/dc_af3db66d573f
How to cite
The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory — arXiv:2610.07309 — arXiv (en), https://arxiv.org/abs/2610.07309 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af3db66d573f (Metraipolis archive dc_af3db66d573f, sha256 1ad12b9aa81bb3dc15052a599e7187e3fe41475e4dbda342a1a74dbabaeef608)
BibTeX
@misc{dcaf3db66d573f,
title = {The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory — arXiv:2610.07309},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07309},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af3db66d573f; sha256 1ad12b9aa81bb3dc15052a599e7187e3fe41475e4dbda342a1a74dbabaeef608},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07309. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term-memory agents can retrieve relevant information that is inadmissible for the current request because it belongs to another principal, violates policy, or reflects an incompatible lifecycle state. Recall and final-answer accuracy do not reveal this: a route can appear safe by missing required evidence, while a correct answer may follow inadmissible prompt exposure. We introduce a retrieval-admissibility verification framework that assigns each memory-query pair one of three statuses (admissible, inadmissible, or unresolved), compares routes at matched required-evidence recall with bounds for unresolved cases, and tracks memory IDs through prompt exposure while linking exposure to target-level disclosure. We evaluate its stages on separate, non-pooled populations. A post-hoc top-20 reanalysis of frozen rankings from two public long-term-memory benchmarks, RHELM and MemOps, covers 3,767 queries. All released anchors lie within trusted query namespaces; with within-namespace scores unchanged, off-namespace filtering cannot lower their ranks. Top-20 anchor recall increases from 0.432 to 0.533, 80% recall feasibility from 0.237 to 0.311, and exact similarity evaluations decrease by 98.3%. In a frozen 72-case development diagnostic, a released-metadata reference preserves required evidence, whereas neither text-only verifier detects violations under the 1% required-anchor false-denial limit. Across 1,523 paired benchmark-native cases, namespace routing is associated with judged-accuracy gains of 0.053-0.068 across three readers; recall also changes, so this comparison is observational. In 16 controlled exposure scenarios, only one of four reader-specific 95% confidence intervals excludes zero for relevant-inadmissible literal disclosure (+0.156, 95% CI [0.031, 0.312]). Results motivate separate verification of candidate support, admissibility, prompt exposure, and answer disclosure. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.07309 — 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 2026-10-07T11:15:09.473Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).