{"slug": "a-mem-agentic-memory-for-llm-agents", "title": "A-Mem: Agentic Memory for LLM Agents", "summary": "Researchers Wujiang Xu and colleagues posted A-MEM, an agentic memory system for LLM agents, to arXiv on 17 February 2025, with the paper last revised 8 October 2025 as version v11. A-MEM follows the Zettelkasten method, generating structured notes with contextual descriptions, keywords and tags for each new memory, then dynamically linking related historical memories and letting new memories trigger updates to existing ones. Experiments across six foundation models showed superior improvement over existing state-of-the-art baselines, with evaluation code at github.com/WujiangXu/A-mem and the system code at github.com/WujiangXu/A-mem-sys.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 17 Feb 2025 (\n\n[v1](https://arxiv.org/abs/2502.12110v1)), last revised 8 Oct 2025 (this version, v11)]\n# Title:A-MEM: Agentic Memory for LLM Agents\n\n[View PDF](https://arxiv.org/pdf/2502.12110)\n\n[HTML (experimental)](https://arxiv.org/html/2502.12110v11)\n\nAbstract: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 [this https URL](https://github.com/WujiangXu/A-mem), while the source code of the agentic memory system is available at [this https URL](https://github.com/WujiangXu/A-mem-sys).\n    \n\n## Submission history\n\nFrom: Wujiang Xu [\n[view email](https://arxiv.org/show-email/8861f1bb/2502.12110)]\n\n**Mon, 17 Feb 2025 18:36:14 UTC (603 KB)**\n\n[\\[v1\\]](https://arxiv.org/abs/2502.12110v1)\n**Mon, 3 Mar 2025 04:14:02 UTC (603 KB)**\n\n[\\[v2\\]](https://arxiv.org/abs/2502.12110v2)\n**Tue, 4 Mar 2025 15:09:10 UTC (603 KB)**\n\n[\\[v3\\]](https://arxiv.org/abs/2502.12110v3)\n**Mon, 14 Apr 2025 15:21:49 UTC (603 KB)**\n\n[\\[v4\\]](https://arxiv.org/abs/2502.12110v4)\n**Fri, 18 Apr 2025 17:26:57 UTC (603 KB)**\n\n[\\[v5\\]](https://arxiv.org/abs/2502.12110v5)\n**Sun, 11 May 2025 18:10:25 UTC (2,620 KB)**\n\n[\\[v6\\]](https://arxiv.org/abs/2502.12110v6)\n**Wed, 21 May 2025 05:16:32 UTC (2,629 KB)**\n\n[\\[v7\\]](https://arxiv.org/abs/2502.12110v7)\n**Tue, 27 May 2025 02:44:13 UTC (1,002 KB)**\n\n[\\[v8\\]](https://arxiv.org/abs/2502.12110v8)\n**Mon, 2 Jun 2025 22:21:21 UTC (995 KB)**\n\n[\\[v9\\]](https://arxiv.org/abs/2502.12110v9)\n**Tue, 15 Jul 2025 00:44:52 UTC (600 KB)**\n\n[\\[v10\\]](https://arxiv.org/abs/2502.12110v10)\n**[v11]** Wed, 8 Oct 2025 01:46:37 UTC (607 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/a-mem-agentic-memory-for-llm-agents", "canonical_source": "https://arxiv.org/abs/2502.12110", "published_at": "2026-09-28 13:35:27+00:00", "updated_at": "2026-09-28 13:47:50.789087+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research", "machine-learning"], "entities": ["A-MEM", "Wujiang Xu", "arXiv", "Zettelkasten", "github.com/WujiangXu/A-mem", "github.com/WujiangXu/A-mem-sys"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/a-mem-agentic-memory-for-llm-agents", "markdown": "https://wpnews.pro/news/a-mem-agentic-memory-for-llm-agents.md", "text": "https://wpnews.pro/news/a-mem-agentic-memory-for-llm-agents.txt", "jsonld": "https://wpnews.pro/news/a-mem-agentic-memory-for-llm-agents.jsonld"}}