Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion, or revocation makes it inadmissible for the current answer. We formalize this as a separation between utility and authority. A fixed finite penalty applied to an unnormalized utility score cannot guarantee exclusion under arbitrary positive-affine reparameterization of that score; by contrast, rank-normalized compensation is scale-invariant and therefore forms a stronger empirical comparator. Our prospectively frozen TIDE/LongMemEval primary was quarantined before a valid HELDOUT comparison because the materialized TIDE adapter conflated historical age with query-relative inadmissibility and the aligned LongMemEval split left no DEV set for the predeclared penalty selection. We therefore report a post-primary replacement diagnostic on Memora Remembering, where update/delete operations provide item-level forgetting state. On Qwen3-8B, DEV selected lambda = 0.6 from a ten-point normalized SOFT family. Across 185 HELDOUT units in 28 dependency clusters, HARD exclusion yields 4.04% balanced construct error versus 19.66% for locked SOFT, a paired difference of 15.61 points with a 20,000-replicate cluster-bootstrap 95% interval of [13.07, 18.76]. The effect is driven primarily by forgotten-value leakage while current-value recall is preserved. This is same-Q operator-comparison evidence, not a universal claim that scalar control fails, not an evaluation of learned authority inference, and not an independent downstream-harm endpoint.
These results establish scope matching as a complementary control for persistent agent memory: certification determines whether an edit is supported, while retrieval scope determines where that evidence authorizes its use.
Ye-Zhou Cheng, Run-Jia Du, Ze-Ming Liu et al.· arXiv.org· 1 citation
Hindsight Memory-PRM exploits this audit trail twice: offline to train an operation-conditioned memory-utility critic, and online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit.
H. Jia, Yang Liu, Ying-Guang Yang et al.· 0 citations
A paired-history audit and label-equivariant repair support a scoped evaluation methodology and reproducible failure analysis and general superiority of the repaired algorithm, not general superiority of the repaired algorithm.
LAM is proposed, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a pe...
Bai-Xi Sun, Le Chen, Anjir Ahmed Chowdhury et al.· 0 citations
The introduction of TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory, and the results establish lifecycle revocation as a core memory operation for agents that must falsify, audit, and later re-promote evolving knowledge.
Yan Zhou, Yue Ouyang, Kaiyang Zheng et al.· 3 citations· ⚡1
Control evaluations reveal that targeted poisoning risk varies across memory operations and motivate stage-aware evaluation and control of LLM-agent memory, showing that targeted poisoning risk varies across memory operations.
Chuan-Chao Zang, Zi-Jian Cao, Xiang-Tao Meng et al.· 0 citations