Agentic Memory for LLM Agents
Researchers from Rutgers University and Ant Group propose a new agentic memory system for LLM agents, addressing the need for long-term memory in complex real-world tasks. Key highlights include:
Ask this paper
Dynamic & Zettelkasten-inspired design â A-MEM autonomously creates comprehensive memory notesâeach with textual attributes (keywords, tags) and embeddingsâthen interlinks them based on semantic similarities. The approach is inspired by the Zettelkasten method of atomic note-taking and flexible linking, but adapted to LLM workflows, allowing more adaptive and extensible knowledge management.
Automatic âmemory evolutionâ â When a new memory arrives, the system not only adds it but updates relevant older memories by refining their tags and contextual descriptions. This continuous update enables a more coherent, ever-improving memory network capable of capturing deeper connections over time.
Superior multi-hop reasoning â Empirical tests on long conversational datasets show that A-MEM consistently outperforms static-memory methods like MemGPT or MemoryBank, especially for complex queries requiring links across multiple pieces of information. It also reduces token usage significantly by selectively retrieving only top-k relevant memories, lowering inference costs without sacrificing accuracy.