Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control

2025-05-23

AI Summary

Addressing security, efficiency, and traceability challenges in cross-user knowledge sharing under dynamic, asymmetric permission constraints in multi-user, multi-agent environments, this paper proposes a hierarchical memory framework. Methodologically, it introduces (1) a novel bipartite-graph-based asynchronous time-varying permission model enabling fine-grained, context-aware memory read/write control; (2) a private–shared dual-tier memory architecture integrating immutable provenance metadata with policy-driven memory projection; and (3) a conditional policy engine for dynamic compliance verification based on system-, user-, and agent-state contexts. Experimental results demonstrate that the framework significantly improves cross-user knowledge reuse efficiency while ensuring provably compliant memory operations and end-to-end auditable traceability across the entire knowledge lifecycle.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Mechanism Design

Application Category

• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent memory has been shown to enhance single-agent performance, most approaches assume a monolithic, single-user context-overlooking the benefits and challenges of knowledge transfer across users under dynamic, asymmetric permissions. We introduce Collaborative Memory, a framework for multi-user, multi-agent environments with asymmetric, time-evolving access controls encoded as bipartite graphs linking users, agents, and resources. Our system maintains two memory tiers: (1) private memory-private fragments visible only to their originating user; and (2) shared memory-selectively shared fragments. Each fragment carries immutable provenance attributes (contributing agents, accessed resources, and timestamps) to support retrospective permission checks. Granular read policies enforce current user-agent-resource constraints and project existing memory fragments into filtered transformed views. Write policies determine fragment retention and sharing, applying context-aware transformations to update the memory. Both policies may be designed conditioned on system, agent, and user-level information. Our framework enables safe, efficient, and interpretable cross-user knowledge sharing, with provable adherence to asymmetric, time-varying policies and full auditability of memory operations.

Problem

• Enabling multi-user memory sharing in LLM agents with dynamic access control
• Addressing knowledge transfer challenges under asymmetric permissions
• Ensuring secure and auditable memory operations in collaborative environments

Innovation

• Dynamic access control via bipartite graphs
• Two-tier memory: private and shared fragments
• Immutable provenance attributes for auditability