# Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents

arXiv: https://arxiv.org/abs/2608.12476 · HTML: https://mlsanity.com/paper/2608.12476/

## 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 20 of its 34 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning](https://mlsanity.com/paper/2601.02163/) (2026)
- [APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI](https://mlsanity.com/paper/2604.14362/) (2026)
- [MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts](https://mlsanity.com/paper/2605.20926/) (2026)
- [TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory](https://mlsanity.com/paper/2606.06240/) (2026)
- [Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation](https://mlsanity.com/paper/2605.25869/) (2026)
- [Text2Mem: A Unified Memory Operation Language for Memory Operating System](https://mlsanity.com/paper/2509.11145/) (2025)
- [StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems](https://mlsanity.com/paper/2607.05844/) (2026)
- [MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory](https://mlsanity.com/paper/2605.07242/) (2026)

## Abstract (arXiv)

Long-term agent memory is usually treated as select--store--retrieve, but retrieval does not decide whether contradictory, superseded, retracted, deleted, or stale records may support an outgoing claim. We introduce Governed Persistent Memory (GPM), an auditable bitemporal state-transition model with source-bound admission, derived lifecycle state, current public barriers, and fail-closed structured release. Five executable clauses cover ledger integrity, source binding, conflict isolation, non-revival after retraction or deletion, and exact claim closure over a fresh view at one verified head. On a prespecified hash-frozen 3,600-case GPM-ReleaseBench, GPM matches all complete outcomes; the strongest of three intentionally simple complete policies matches 1,800/3,600 and makes unmatched releases on 50% of violation cases. A separate sealed end-to-end service evaluation exercises real ingestion and release across eight query families. In its publicly disclosed V3 arm, the governed lane is correct on 2,400/2,400 clusters versus 600/2,400 for ungoverned local Qwen2.5-7B; it repairs all 1,800 baseline failures with no regression (one-sided 95% lower bounds 99.875% and 99.834%). A later V5 reseal over Chinese- and English-command arms, with generation-date pinning and no post-freeze reducer amendment, again obtains 2,400/2,400 per arm. A production-code-independent finite model explores 331,776 semantic and 1,990,656 query states without a full-contract counterexample, and a 100,000-trace three-engine differential yields zero mismatches. These are bounded contract and implementation results, not open-world model accuracy or evidence of world truth. Governed answers in the sealed service evaluation are deterministic service outputs; the 7B result is the ungoverned comparison, not a claim that a language model itself became perfectly accurate.