MemArchitect: A Policy Driven Memory Governance Layer
Not on the map. Why?
Abstract (arXiv)
Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions, enforce privacy, or prevent outdated information ("zombie memories") from contaminating the context window. We introduce MemArchitect, a governance layer that decouples memory lifecycle management from model weights. MemArchitect enforces explicit, rule-based policies, including memory decay, conflict resolution, and privacy controls. We demonstrate that governed memory consistently outperforms unmanaged memory in agentic settings, highlighting the necessity of structured memory governance for reliable and safe autonomous systems.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 18 Mar 2026.
Builds on
12 of 18 references.
References · 12
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
- 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
- 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
- 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
- 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
- 2024Titans: Learning to Memorize at Test Timecited by 303
- 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 279
- 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 163
- 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 142
- 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systemscited by 7
- 2026The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agentscited by 0
- 2026Reliability Engineering for AI Systems: Challenges, Methods, and Directionscited by 0
- 2026Reliability Engineering for AI Systems: Challenges, Methods, and Directions28 Sep 2026
- 2026The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents26 Sep 2026
- 2026Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems25 May 2026
Similar, not cited
Close in wording, no citation either way
- 2026Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework
- 2026A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
- 2026PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
- 2026Are We Ready For An Agent-Native Memory System?
- 2026Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
- 2026GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
- 2026Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
- 2026MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing