A-MEM: Agentic Memory for LLM Agents
2025/02/17 by Wujiang Xu, Zujie Liang, Xu, Wujiang +9 · 3 voices · 251 citations
Engineering · Computer Science · #cs.CL #cs.HC
paper · pdf · doi:10.48550/arxiv.2502.12110
Abstract
While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack sophisticated memory organization, despite recent attempts to incorporate graph databases. Moreover, these systems' fixed operations and structures limit their adaptability across diverse tasks. To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. Following the basic principles of the Zettelkasten method, we designed our memory system to create interconnected knowledge networks through dynamic indexing and linking. When a new memory is added, we generate a comprehensive note containing multiple structured attributes, including contextual descriptions, keywords, and tags. The system then analyzes historical memories to identify relevant connections, establishing links where meaningful similarities exist. Additionally, this process enables memory evolution - as new memories are integrated, they can trigger updates to the contextual representations and attributes of existing historical memories, allowing the memory network to continuously refine its understanding. Our approach combines the structured organization principles of Zettelkasten with the flexibility of agent-driven decision making, allowing for more adaptive and context-aware memory management. Empirical experiments on six foundation models show superior improvement against existing SOTA baselines. The source code for evaluating performance is available at https://github.com/WujiangXu/A-mem, while the source code of the agentic memory system is available at https://github.com/WujiangXu/A-mem-sys.
Cited by
- Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory
- Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
- MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
- ACM: Agentic Context Management for Long Horizon Tasks
- ClawRec: A Claw-Native Recommender System
- Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering
- LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory
- Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement
- RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation
- SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent
- Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management
- ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction
- Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
- MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents
- Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
- A Network Arena for Benchmarking AI Agents on Network Troubleshooting
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models
- AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation
- Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM
- Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
- Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
- Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
- PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
- MemLoRA: Distilling Expert Adapters for On-Device Memory Systems
- Personalizing Agent Privacy Decisions via Logical Entailment
- MemVerse: Multimodal Memory for Lifelong Learning Agents
- Network Self-Configuration based on Fine-Tuned Small Language Models
- Real-Time Procedural Learning From Experience for AI Agents
- Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
- Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
- Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge
- General Agentic Memory Via Deep Research
- A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
- MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists
- Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures
- LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering
- O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
- LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
- Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning
- BudgetMem: Learning Selective Memory Policies for Cost-Efficient Long-Context Processing in Language Models
- Cache Mechanism for Agent RAG Systems
- MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
- Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse
- EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory
- Dynamic Affective Memory Management for Personalized LLM Agents
- Context Engineering 2.0: The Context of Context Engineering
- MemTX: Transactional Belief Commit for Stateful Agent Memory
- Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants
- WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback
- Metis: Memory Foundation Model
- Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
- DMF: A Deterministic Memory Framework for Conversational AI Agents
- Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval
- Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft
- Understanding LoRA as Knowledge Memory: An Empirical Analysis
- RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
- AgentFold: Long-Horizon Web Agents with Proactive Context Management
- WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
- Evaluating Long-Term Memory for Long-Context Question Answering
- LLM-empowered knowledge graph construction: A survey
- Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
- MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
- Can Tool-Integrated Reinforcement Learning Generalize Across Diverse Domains?
- How2: How to learn from procedural How-to questions
- A Survey on Agentic Multimodal Large Language Models
- PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency
- AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
- Preference-Aware Memory Update for Long-Term LLM Agents
- Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
- Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent
- The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
- LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- JoyAgent-JDGenie: Technical Report on the GAIA
- TokMem: Tokenized Procedural Memory for Large Language Models
- Mem-α: Learning Memory Construction via Reinforcement Learning
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
- Agentic Services Computing
- Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
- Estimating the Empowerment of Language Model Agents
- EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
- SGMem: Sentence Graph Memory for Long-Term Conversational Agents
- MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
- MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck
- ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs
- ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent Memory
- Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
- SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge
- AutoMem: Automated Learning of Memory as a Cognitive Skill
- Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
- How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
- LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
- EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments
- SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing
- From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
- A Scenario-Driven Cognitive Approach to Next-Generation AI Memory
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
- Text2Mem: A Unified Memory Operation Language for Memory Operating System
- AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise
- Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue
- Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
- Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures
- PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
- Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
- Memp: Exploring Agent Procedural Memory
- Training-Free Multimodal Large Language Model Orchestration
- RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
- Nemori: Self-Organizing Agent Memory Inspired by Cognitive Science
- A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
- L3M+P: Lifelong Planning with Large Language Models
- DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
- MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
- Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects
- A Novel Self-Evolution Framework for Large Language Models
- Eywa: Provenance-Grounded Long-Term Memory for AI Agents
- Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
- Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
- Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture
- Know It, Act on It: Investigating Memory Utilization in LLM Personalization
- Beyond Retrieval: Analytic Memory for Multimodal Agents
- MIRIX: Multi-Agent Memory System for LLM-Based Agents
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework
- ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
- Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
- Reproducing LightMem: Naive RAG Is Just as Good for Memory Management
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- MemOS: A Memory OS for AI System
- MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
- The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems
- AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles
- A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
- A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications
- Memory as a Service (MaaS): Purpose-Bound Memory Mediation for Cooperative Agents
- G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
- HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants
- Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws
- Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
- MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
- Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
- OAgents: An Empirical Study of Building Effective Agents
- Towards Pervasive Distributed Agentic Generative AI -- A State of The Art
- EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair
- MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
- Memory OS of AI Agent
- 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
- From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
- Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
- When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary
- FedWorld: Scope-Aware Federation of Agent World Models
- Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering
- MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
- PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents
- CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
- MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents
- How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
- CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents
- V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory
- PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents
- TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents
- Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents
- MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
- CrystalMem: Elastic Memory for Self-Evolving LLM Agents via Knowledge Crystallization
- Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agents
- Personalizing Large Language Model Agents with Small Policy Models
- AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
- HUSH-Bench: Measuring Memory-Use Boundaries for Sensitive History in Conversational Agents
- AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
- Applying Cognitive Design Patterns to General LLM Agents
- MARK: Memory Augmented Refinement of Knowledge
- Terminal Agents Suffice for Enterprise Automation
- EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
- ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
- D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing
- STAGE: A Full-Screenplay Benchmark for Reasoning over Evolving Stories
- Large Language Models Do Not Always Need Readable Language
- AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
- AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition
- StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
- From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
- Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory
- Recursive Models for Long-Horizon Reasoning
- Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
- One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
- SWE Context Bench: A Benchmark for Context Learning in Coding
- On the Failure of Latent State Persistence in Large Language Models
- Can Memory-Augmented LLM Agents Aid Journalism in Interpreting and Framing News for Diverse Audiences?
- CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios
- Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
- Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent
- From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
- MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents
- Self-GC: Self-Governing Context for Long-Horizon LLM Agents
- Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
- From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
- Learning Agent-Compatible Context Management for Long-Horizon Tasks
- Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
- GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
- MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
- Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
- Coding Agents are Effective Long-Context Processors
- Continuum Memory Architectures for Long-Horizon LLM Agents
- Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems
- AIBuildAI: An AI Agent for Automatically Building AI Models
- Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
- G2-Reader: Dual Evolving Graphs for Multimodal Document QA
- Meta Context Engineering via Agentic Skill Evolution
- EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents
- XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being
- MemoBrain: Executive Memory as an Agentic Brain for Reasoning
- Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
- DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
- Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- SimpleMem: Efficient Lifelong Memory for LLM Agents
- LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
- SkillJack: Persistent Skill Backdoors in Self-Evolving Agents
- Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
- Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems
- MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
- FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents
- CURATE: Leveraging LLM Agents to Compose, Catalog, and Deploy Reproducible Workflows
- SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
- Contextual Agentic Memory is a Memo, Not True Memory
- CogniFold: Always-On Proactive Memory via Cognitive Folding
- From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
- Planet as a Brain: Towards Internet of AgentSites based on AIOS Server
- MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation
- When Do Prompt-Side Agent Playbooks Transfer? Accuracy, Cost, and Runtime Shift in Agent Deployment
- ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution
- Unified Agent: Managing Interactions across Devices
- From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models
- Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering
- ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control
- Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
- A Survey of Personalization: From RAG to Agent
Discussions
Related