MemArchitect: A Policy Driven Memory Governance Layer
Lingavasan Suresh Kumar, Yang Ba, Rong Pan

TL;DR
MemArchitect introduces a policy-driven memory management layer for LLM agents, addressing governance gaps by enforcing rules for privacy, decay, and conflict resolution, thereby improving reliability and safety.
Contribution
It proposes MemArchitect, a novel governance layer that decouples memory management from model weights and enforces explicit policies for better control.
Findings
Governed memory outperforms unmanaged memory in agentic tasks
Structured memory governance enhances reliability and safety
MemArchitect effectively manages privacy and conflict resolution
Abstract
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frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions, enforce privacy, or prevent outdated information ("zombie memories") from contaminating the context window.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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSecurity and Verification in Computing · Personal Information Management and User Behavior · Adversarial Robustness in Machine Learning
