Memory as Middleware for Self-Improving AI Agents

arXiv:2609.32091 · cs.AI, cs.DC · Submitted 2026-09-25 · Read on arXiv

cs.AI, cs.DC

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/AgentToolkit/altkevolve

Project page: https://agents.md

Terminology

• Provenance — 27× in this paper · explained in 4 episodes
• Agent Memory — 22× in this paper · explained in 1 episode
• Consistency — 20× in this paper · explained in 3 episodes
• AI Agents — 10× in this paper · explained in 2 episodes
• Trace — 10× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Abstraction — 5× in this paper · explained in 1 episode
• Personalization — 4× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Agent Skills — 1× in this paper · explained in 1 episode
• Agentic Coding — 1× in this paper · explained in 1 episode
• Agentic Memory System — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
• Titans: Learning to Memorize at Test Time
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
• When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
• On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
• Larimar: Large Language Models with Episodic Memory Control
• Trajectory-Informed Memory Generation for Self-Improving Agent Systems
• Memp: Exploring Agent Procedural Memory
• MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
• Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation
• Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework
• A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
• A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
• EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
• Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory
• MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
• SkillOS: Learning Skill Curation for Self-Evolving 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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection