Skip to content

Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory

Sep 2026 · 0 citations · 38 references
Computer Science

Abstract

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.

View source

Similar papers

#natural language process... Preprint Aug 2026

Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit

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
#artificial intelligence Preprint Sep 2026

LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound

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
Preprint Aug 2026

TEPA: Revoking Stale Memories for Conflict-Robust Language Agents

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
Preprint Aug 2026

Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory

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

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.