Metraipolis › archive › dc_6997d851ee72
What to Admit and How to Present: Governing Persistent Memory in LLM Agents — arXiv:2610.11188
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11188
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:47:31.421Z
- SHA-256 of the archived text
f35d8b5948d5468db2560006d08fbba763973a0422e1f491c1b6bce29ae125a9- Stable URL of this page
https://metraipolis.com/documento/dc_6997d851ee72
How to cite
What to Admit and How to Present: Governing Persistent Memory in LLM Agents — arXiv:2610.11188 — arXiv (en), https://arxiv.org/abs/2610.11188 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6997d851ee72 (Metraipolis archive dc_6997d851ee72, sha256 f35d8b5948d5468db2560006d08fbba763973a0422e1f491c1b6bce29ae125a9)
BibTeX
@misc{dc6997d851ee72,
title = {What to Admit and How to Present: Governing Persistent Memory in LLM Agents — arXiv:2610.11188},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11188},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6997d851ee72; sha256 f35d8b5948d5468db2560006d08fbba763973a0422e1f491c1b6bce29ae125a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11188. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decisions: admission, which determines what recalled information enters the working context, and presentation, which determines how admitted information is expressed. We implement two inference-time designs without retraining: factor-compiled admission (FC), which assesses whole memory entries, and permission-semantic admission (PS), which decomposes entries into typed units; both translate adjudicated attributes into eligibility decisions via deterministic policies. We evaluate on a four-backbone development suite and an external benchmark with four tasks of 300 samples each. Relative to verbatim injection, FC and PS reduce pooled judge-assessed failure rates on the external benchmark by 6.7 and 8.8 percentage points (p = 2.7e-7 and 4.1e-12), and development-set cross-domain leakage falls by up to 29.5 percentage points. A query-conditioned gating baseline shows no significant change in objective-fact failure or pooled failure. Under matched admission budgets, PS outperforms random and relevance-based selection on external objective-fact judgment after Holm correction. Holding presentation fixed, tightening admission cuts cross-domain failure by a further 17.5 percentage points (p = 1.6e-4); in contrast, no comparison between two renderings of identical adjudicated outputs survives multiple-comparison correction. Both designs increase personalization failures, and PS misses the preregistered improvement and personalization-preservation criteria. These results support evaluating admission and presentation separately: selection quality provides task-specific safety gains, while preserving beneficial memory use remains unresolved. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.11188 — 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 2026-10-09T05:47:00.593Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).