What to Admit and How to Present: Governing Persistent Memory in LLM Agents
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- DeepSeek-V3 Technical Report
- Mitigating Over-Personalization in LLMs via Structured Memory
- Kimi K2: Open Agentic Intelligence
- MiniMax Sparse Attention
- TOFU: A Task of Fictitious Unlearning for LLMs
- MemGPT: Towards LLMs as Operating Systems
- Qwen3 Technical Report
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
- MIRIX: Multi-Agent Memory System for LLM-Based Agents
- State Contamination in Memory-Augmented LLM Agents
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Adaptive Memory Admission Control for LLM Agents
- 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