GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
For developers of LLM-based shared assistants in institutional settings, this benchmark reveals that current memory agents are unreliable for multi-user deployments.
GateMem benchmarks multi-principal shared-memory agents across utility, access control, and forgetting. No existing method achieves strong performance on all three; long-context prompting yields the best governance but at high cost, while retrieval-based methods leak information.
Memory benchmarks for LLM agents largely assume single-user settings, leaving shared assistants for hospitals, workplaces, campuses, and households understudied. In these deployments, multiple principals write to a common memory pool and query it under different roles, scopes, and relationships, so memory quality requires governance as well as recall. We introduce GateMem, a benchmark for multi-principal shared-memory agents. GateMem jointly evaluates utility for legitimate long-horizon requests with state updates, access control across contextual authorization boundaries, and agent-facing active forgetting after explicit deletion requests. It spans medical, office, education, and household domains, with long-form multi-party episodes, incremental memory injection, hidden checkpoints, structured judging, and leak-target annotations. Across diverse baselines and backbone models, no method simultaneously achieves strong utility, robust access control, and reliable forgetting. Long-context prompting often yields the best governance score at high token cost, while retrieval-based and external-memory methods reduce cost yet still leak unauthorized or deleted information. These results show current memory agents remain far from reliable shared institutional deployment.