# What to Admit and How to Present: Governing Persistent Memory in LLM Agents

arXiv: https://arxiv.org/abs/2610.11188 · HTML: https://mlsanity.com/paper/2610.11188/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 16 of 16)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [MiniMax Sparse Attention](https://mlsanity.com/paper/2606.13392/) (2026)
- [Adaptive Memory Admission Control for LLM Agents](https://mlsanity.com/paper/2603.04549/) (2026)
- [Beyond Similarity: Trustworthy Memory Search for Personal AI Agents](https://mlsanity.com/paper/2606.06054/) (2026)
- [MemSyco-Bench: Benchmarking Sycophancy in Agent Memory](https://mlsanity.com/paper/2607.01071/) (2026)
- [Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents](https://mlsanity.com/paper/2605.17641/) (2026)
- [State Contamination in Memory-Augmented LLM Agents](https://mlsanity.com/paper/2605.16746/) (2026)
- [Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models](https://mlsanity.com/paper/2606.10949/) (2026)
- [Mitigating Over-Personalization in LLMs via Structured Memory](https://mlsanity.com/paper/2608.08300/) (2026)

## Abstract (arXiv)

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.