LATIDIA · Investigación

Qué admitir y cómo presentar: gobernar la memoria persistente en los agentes de LLM

arXiv:2610.11188v1 Announce Type: new Resumen: La memoria persistente puede mejorar la personalización en los agentes LLM, pero también puede inducir adulación y fugas entre dominios. Distinguimos dos decisiones de gobernanza: admisión, WHI

La noticia

arXiv:2610.11188v1 Announce Type: new Abstract: 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