Agent Memory as Rate-Limited Filtering: Explicit State Outlasts Long Context Beyond a Reader-Dependent Horizon
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
- STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
- Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons
- Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression
- MemGPT: Towards LLMs as Operating Systems
- Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length
- Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis