A Survey on the Memory Mechanism of Large Language Model-based Agents

By Zeyu Zhang, Quanyu Dai, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Jieming Zhu, Zhenhua Dong. ACM Trans. Inf. Syst., 2024

647 citations recorded by the source corpus.

Large language model (LLM)-based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions. The key component to support agent-environment interactions is the memory of the agents. While previous studies have proposed many promising memory mechanisms, they are scattered in different papers, and there lacks a systematical review to summarize and compare these works from a holistic perspective, failing to abstract common and effective designing patterns for inspiring future studies. To bridge this gap, in this article, we propose a comprehensive survey on the memory mechanism of LLM-based agents. In specific, we first discuss “what is” and “why do we need” the memory in LLM-based agents. Then, we systematically review previous studies on how to design and evaluate the memory module. In addition, we also present many agent applications, where the memory module plays an important role. At last, we analyze the limitations of existing work and show important future directions. To keep up with the latest advances in this field, we create a repository at https://github.com/nuster1128/LLM_Agent_Memory_Survey.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/b6ab16c8eade03a39830493071d99fc48a736fac

Citations in the corpus

• Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG (2025, neutral): “Short-term memory [23] tracks immediate conversation state, while long-term memory [23]stores accumulated knowledge and agent experiences.”
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs (2025, neutral): “They excel in knowledge memorization, enabling distributed agents to retain and share diverse knowledge bases without overloading a single system [51, 154].”
• Choosing How to Remember: Adaptive Memory Structures for LLM Agents (2026, unknown): “…performance, as different tasks exhibit distinct structural characteristics and interaction patterns (Trach & McDougle, 2025; Cellier et al., 2022; Zhang et al., 2025b), such as topic evolution, temporal progression, and relational dependencies, that often co-occur in long-horizon conversations.”
• Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection (2026, unknown): “Rather than treating the model as immutable, self-evolving agents continually update their behavior through interaction and feedback, evolving their memory, prompts, tools, or parameters as new experience accumulates (Gao et al., 2025a; Zhang et al., 2025c).”
• Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction (2025, unknown): “These include memory-based methods, which utilize an external memory to store and dynamically update the context [30, 31]; RAG, which”
• SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution (2026, unknown): “Memory increasingly serves as a fundamental component in modern LLM-based agentic framework to support multi-step decision making (Zhang et al., 2025; Hu et al., 2025b).”