The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory

arXiv:2610.07309 · cs.AI, cs.IR, cs.MA · Submitted 2026-10-05 · Read on arXiv

cs.AI, cs.IR, cs.MA

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: 26 pages. Accepted at the NeurIPS 2026 Workshop "Who Verifies the Agents? Toward Reliable Agent Development". Code: https://github.com/ziwang11112/right-memory-wrong-context

Code: https://github.com/ziwang11112/right-memory-wrong-context

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Admissibility — 1× in this paper · explained in 2 episodes
• Agent Memory — 1× in this paper · explained in 1 episode

Sources

• SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
• STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
• Selection Integrity for LLM Graph Memory: An Accumulability Criterion for Information-Flow-Blind Retrieval
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
• MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents
• MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery
• Governed Shared Memory for Multi-Agent LLM Systems
• GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
• Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
• A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
• MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts
• MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
• LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
• RaMem: Contextual Reinstatement for Long-term Agentic Memory
• Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
• Beyond Similarity: Trustworthy Memory Search for Personal AI Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems