# Agent memory systems

Area: [LLM agents and tool use](https://mlsanity.com/agents/index.md). HTML: https://mlsanity.com/agents/agent-memory-systems/

## Key facts

- Agent memory systems: 718 papers on arXiv since 2023 (data through 7 Oct 2026).
- 300 of its 718 mapped papers (42%) cite “A-MEM: Agentic Memory for LLM Agents” (2025, arXiv 2502.12110).
- 276 of its 718 mapped papers (38%) cite “Evaluating Very Long-Term Conversational Memory of LLM Agents” (2024, arXiv 2402.17753).
- 90 new papers 17 Sep–7 Oct.

## Most cited here

- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025), cited by 300 papers here
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024), cited by 276 papers here
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025), cited by 210 papers here
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024), cited by 151 papers here
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025), cited by 150 papers here
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025), cited by 95 papers here
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025), cited by 85 papers here
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025), cited by 73 papers here
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025), cited by 67 papers here
- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025), cited by 66 papers here

## New (17 Sep–7 Oct)

- [Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback](https://mlsanity.com/paper/2610.11007/) (2026-10-07)
- [VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding](https://mlsanity.com/paper/2610.10183/) (2026-10-07)
- [HGP:An on-device personalized agent memory via hybrid graph storage](https://mlsanity.com/paper/2610.10071/) (2026-10-07)
- [Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents](https://mlsanity.com/paper/2610.09590/) (2026-10-07)
- [Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA](https://mlsanity.com/paper/2610.09348/) (2026-10-07)
- [Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory](https://mlsanity.com/paper/2610.09008/) (2026-10-06)
- [Towards In-Parameter Memory Augmentation for Large Language Models](https://mlsanity.com/paper/2610.08630/) (2026-10-06)
- [MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory](https://mlsanity.com/paper/2610.08586/) (2026-10-06)
- [How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation](https://mlsanity.com/paper/2610.08514/) (2026-10-06)
- [DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents](https://mlsanity.com/paper/2610.08102/) (2026-10-06)
- [ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents](https://mlsanity.com/paper/2610.07863/) (2026-10-06)
- [Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell](https://mlsanity.com/paper/2610.07782/) (2026-10-06)
- [MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments](https://mlsanity.com/paper/2610.07376/) (2026-10-05)
- [Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory](https://mlsanity.com/paper/2610.07311/) (2026-10-05)
- [AMBER: Training Long-Horizon Web Agents through Append-Only Memory](https://mlsanity.com/paper/2610.07118/) (2026-10-05)
- [MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents](https://mlsanity.com/paper/2610.06830/) (2026-10-05)
- [VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding](https://mlsanity.com/paper/2610.06672/) (2026-10-05)
- [Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents](https://mlsanity.com/paper/2610.05833/) (2026-10-05)
- [PACMI: Provenance-Aware Cascading Memory Invalidation for Long-Term LLM Agents](https://mlsanity.com/paper/2610.05732/) (2026-10-05)
- [CASE: Cost-Aware Stopping for Efficient Long-Video Agents](https://mlsanity.com/paper/2610.05400/) (2026-10-04)
- [Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures](https://mlsanity.com/paper/2610.05223/) (2026-10-04)
- [AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems](https://mlsanity.com/paper/2610.05176/) (2026-10-04)
- [Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy](https://mlsanity.com/paper/2610.05162/) (2026-10-04)
- [Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory](https://mlsanity.com/paper/2610.05124/) (2026-10-04)
- [MemTrace: State-Consistent Memory for Long-Horizon Coding Agents](https://mlsanity.com/paper/2610.04838/) (2026-10-04)
- [Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It](https://mlsanity.com/paper/2610.04794/) (2026-10-03)
- [When Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model Agents](https://mlsanity.com/paper/2610.03902/) (2026-10-02)
- [DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users](https://mlsanity.com/paper/2610.03020/) (2026-10-02)
- [Continual Graph Memory for Mathematical Research Agents](https://mlsanity.com/paper/2610.02945/) (2026-10-02)
- [Harnessing LLMs as Agents: What Does It Cost?](https://mlsanity.com/paper/2610.02488/) (2026-10-01)