A-MEM: Agentic Memory for LLM Agents

TL;DR

This work addresses the challenge of endowing LLM agents with durable, flexible memory that can evolve over time during long-term interactions.It introduces A-Mem, a Zettelkasten-inspired agentic memory system that constructs atomic notes with rich attributes, employs embedding-based retrieval, and autonomously links and evolves memories through agentic decision making.A-Mem features an autonomous update mechanism with link generation and memory evolution, enabling the memory network to reveal higher-order patterns as experiences accumulate.Empirical evaluation across six foundation models on LoCoMo and DialSim demonstrates superior performance and efficiency compared to baselines, supported by ablations and memory-structure visualizations.

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.

Figures (5)

• Figure 1: Traditional memory systems require predefined memory access patterns specified in the workflow, limiting their adaptability to diverse scenarios. Contrastly, our A-Mem enhances the flexibility of LLM agents by enabling dynamic memory operations.
• Figure 2: Our A-Mem architecture comprises three integral parts in memory storage. During note construction, the system processes new interaction memories and stores them as notes with multiple attributes. The link generation process first retrieves the most relevant historical memories and then employs an LLM to determine whether connections should be established between them. The concept of a 'box' describes that related memories become interconnected through their similar contextual descriptions, analogous to the Zettelkasten method. However, our approach allows individual memories to exist simultaneously within multiple different boxes. During the memory retrieval stage, we extract query embeddings using a text encoding model and search the memory database for relevant matches. When related memory is retrieved, similar memories that are linked within the same box are also automatically accessed.
• Figure 3: Impact of memory retrieval parameter k across different task categories with GPT-4o-mini as the base model. While larger k values generally improve performance by providing richer historical context, the gains diminish beyond certain thresholds, suggesting a trade-off between context richness and effective information processing. This pattern is consistent across all evaluation categories, indicating the importance of balanced context retrieval for optimal performance.
• Figure 4: T-SNE Visualization of Memory Embeddings Showing More Organized Distribution with A-Mem (blue) Compared to Base Memory (red) Across Different Dialogues. Base Memory represents A-Mem without link generation and memory evolution.
• Figure 5: T-SNE Visualization of Memory Embeddings Showing More Organized Distribution with A-Mem (blue) Compared to Base Memory (red) Across Different Dialogues. Base Memory represents A-Mem without link generation and memory evolution.