A survey on the memory mechanism of large language model based agents. A repo lists papers related to LLM based agent.

A survey on the memory mechanism of large language model based agents. The rise and potential of large language model based agents: a survey. 本文是一篇对基于大语言模型的智能体记忆机制的综述，介绍了记忆机制的定义、设计、评估、应用和局限性。文章还对比了其他相关的大语言模型研究，如多模态、压缩和加速等。 Apr 22, 2024 · This paper offers a valuable survey of the memory mechanisms used in large language model-based agents. Mar 22, 2024 · Autonomous agents have long been a research focus in academic and industry communities. Apr 15, 2024 · Abstract In the realm of artificial intelligence, the adaptation of Large Language Model (LLM)-based agents to execute tasks via natural language prompts represents a significant advancement, notably eliminating the need for explicit retraining or fine tuning for fixed-answer tasks such as common sense questions and yes/no queries. Recently, through the acquisition of vast amounts Sep 18, 2023 · The rise and potential of large language model based agents: A survey. Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. org) Introduction基于大语言模型（LLM）的智能体最近引起了研究界和工业界的广泛关注。与原始LLM相比，基于LLM的… To bridge this gap, in this paper, we propose a comprehensive survey on the memory mechanism of LLM-based agents. arXiv preprint arXiv:2309. 最近的相关研究包括：1. , LLM-based agents. Notes: 这篇来自复旦和米哈游团队，涵盖了670多篇参考文献，涉及到的概念和技术范围更广，兼顾科普和科研性质。 Feb 1, 2024 · Computational experiments have emerged as a valuable method for studying complex systems, involving the algorithmization of counterfactuals. - WooooDyy/LLM-Agent-Paper-List A Survey on the Memory Mechanism of Large Language Model based Agents https: //arxiv. The key component to support agent-environment interactions is [ 2404. Abstract: Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Then, we systematically review previous studies on how to design and evaluate the memory module. 2. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness or suboptimal performance in complex agent-related Aug 23, 2023 · 📍 This is the first released and published survey paper in the field of LLM-based autonomous agents. May 20, 2025 · A Survey on the Memory Mechanism of Large Language Model based Agents Aug 22, 2023 · Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. LLMs are playing a significant role in advancement of AI agents. Notes: 这篇来自复旦和米哈游团队，涵盖了670多篇参考文献，涉及到的概念和技术范围更广，兼顾科普和科研性质。 Apr 8, 2025 · 论文精读记录—2025年4月——大模型综述相关——A Survey on the Memory Mechanism of Large Language Model based Agents Feb 1, 2024 · Computational experiments have emerged as a valuable method for studying complex systems, involving the algorithmization of counterfactuals. To address this limitation, the integration of Sep 14, 2023 · For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. These models are based on neural networks and considered as pre-trained, large-scale, statistical language models. A Survey on the Memory Mechanism of Large Language Model based Agents 本文是LLM系列文章，针对《A Survey on the Memory Mechanism of Large Language Model based Agents》的翻译。 Abstract—The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i. The authors propose a unified framework for designing LLM-based agents, encompassing profiling, memory, planning, and action modules. 2 Surveys on Large Language Model-based Agents Based on the capability of LLMs, people have conducted a lot of studies on building LLM-based agents, which can autonomously perceive environments, take actions, accumulate knowledge, and evolve themselves. Dec 17, 2024 · Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. 13501 (2024). Jun 9, 2025 · The memory module functions through three key operations: memory writing, which converts environmental feedback into stored content; memory management, which optimizes information through abstraction, merging, and forgetting; and memory retrieval, which extracts relevant information based on the current context to guide decision-making. Jul 2, 2025 · To bridge this gap, in this paper, we propose a comprehensive survey on the memory mechanism of LLM-based agents. This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy, linking We would like to show you a description here but the site won’t allow us. arXiv preprint arXiv:2404. Apr 21, 2024 · This paper reviews previous studies on how to design and evaluate the memory module for LLM-based agents, which are featured in their self-evolving capability. Sep 27, 2024 · In this survey, since this is an interdisciplinary field, we first introduce the background of agent-based modeling and simulation and large language model-empowered agents. com/nuster1128/LLM_Agent_Memory_Survey 推荐阅读 • 对齐LLM偏好的直接偏好优化方法：DPO、IPO、KTO • 2024：ToB、Agent、多模态 • TA们的RAG真正投产了吗？（上） A Survey on the Memory Mechanism of Large Language Model based Agents (2024) This paper comprehensively surveys LLM-based agents' memory mechanisms, reviewing design and evaluation, presenting applications, and suggesting future directions. 🧠 Memory is the Backbone of LLM-Based Agents In the race toward Artificial General Intelligence (AGI), Large Language Model (LLM)-based agents are evolving fast. The key component to support agent-environment interactions is Jul 11, 2025 · Download Citation | A Survey on the Memory Mechanism of Large Language Model based Agents | Large language model (LLM) based agents have recently attracted much attention from the research and Apr 23, 2024 · TL;DR: This comprehensive survey explores the memory mechanisms of Large Language Model (LLM) based agents, discussing the necessity, design, evaluation, applications, limitations, and future directions of memory in LLM-based agents. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. AI agents are artificial entities that sense their environment, make decisions, and take actions. e. We would like to show you a description here but the site won’t allow us. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness or suboptimal performance in complex agent-related Nov 18, 2024 · 文章浏览阅读440次。一篇survey总结LLM记忆的，实现上总结了三个要素：Source，Forms，Operations。_a survey on the memory mechanism of large language model based agents Mar 16, 2025 · With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and makes the agents hard to achieve human-like decisions. TL;DR: This comprehensive survey explores the memory mechanisms of Large Language Model (LLM) based agents, discussing the necessity, design, evaluation, applications, limitations, and future directions of memory in LLM-based agents. This survey provides an overview of the evolution, capabilities, and applications of LLM-based data agents, highlighting their role in simplifying complex data tasks and lowering the entry barrier for users Abstract Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Sep 18, 2023 · The rise and potential of large language model based agents: A survey. 《A Survey of Memory in Reinforcement Learning》；2. Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable May 11, 2024 · Memory Mechanisms and Linguistic Representation: This session will analyze the similarities between LLMs and human memory and will discuss the mechanisms of storage and formation of the linguistic representation in LLMs. Jan 7, 2024 · Intelligent agents stand out as a potential path toward artificial general intelligence (AGI). . Benefiting from recent progress in large language models (LLMs), LLM-based agents that use universal natural language as an interface exhibit robust generalization capabilities across various applications -- from Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. 《Memory-Augmented Monte Carlo Tree Search for General Video Game Playing》等。 A Survey on the Memory Mechanism of Large Language Model based Agents Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, Ji-Rong Wen. The paper reviews previous studies, designs, and evaluations of memory modules for LLM-based agents, and provides code and data for reproducibility. 21 hours ago · LLMs：《A Survey on the Optimization of Large Language Model-based Agents》翻译与解读导读：这篇论文全面综述了LLM-based agent的优化方法，将其分为参数驱动和参数自由两大类。对基于LLM的智能体优化方法进行了全面的综述，填补了该领域的空白。参数驱动方法侧重于通过微调、强化学习和混合策略来 Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. This paper investigates scenarios involving the Keywords natural language processing, large language models, LLM-based agents, AI agents, agent society Citation Xi Z H, Chen W X, Guo X, et al. We are witnessing the emergence of LLM agents—intelligent entities powered by large language models that can perceive environments, reason about goals, and execute actions autonomously. In specific, we first discuss “what is” and “why do we need” the memory in LLM-based agents. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and thus makes the agents hard to achieve human-like decisions. It provides a detailed overview of the current state of the art, highlighting the diverse approaches and techniques employed to enable these models to store, retrieve, and utilize information. 13501. 4 Dec 31, 2023 · Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. 13501] A Survey on the Memory Mechanism of Large Language Model based Agents (arxiv. Abstract Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Recently, LLM-based agent systems have rapidly evolved from single-agent planning or decision-making to operating as multi-agent systems May 6, 2024 · A Survey on the Memory Mechanism of Large Language Model based Agents（基于大型语言模型的智能体记忆机制调查）支持智能体与环境交互的关键要素是智能体的记忆：为了实现人工通用智能（AGI）的最终目标，智能机器应该能够通过自主探索现实世界并从中学习来提高自己内存的作用：如何积累知识处理历史 A repo lists papers related to LLM based agent. 《Memory-Augmented Reinforcement Learning for Robot Navigation》；3. 2024. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training Apr 19, 2024 · Abstract Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. It compares textual and parametric memories, emphasizing trade-offs between direct interpretability and efficiency. May 6, 2024 · 文章探讨了基于大型语言模型的智能体如何通过记忆机制积累知识、处理历史经验，以及在环境交互中的关键作用。文章强调了记忆在认知心理学、自我进化和应用中的重要性，同时比较了文本形式和参数形式记忆的优缺点，并讨论了未来研究的方向，如记忆同步和终身学习。摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 > A Survey on the Memory Mechanism of Large Language Model based Agents（基于大型语言模型的智能体记忆机制调查）与环境互动并从环境中学习是基于 LLM 的智能体的基本要求。在智能体与环境的交互过程中，有三个关键阶段：经验积累。 Apr 21, 2024 · This is a GitHub repository for a survey paper on the memory mechanism of large language model based agents, published on arXiv in 2024. View recent discussion. Paper link: A Survey on Large Language Model based Autonomous Agents To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The survey also highlights challenges and future directions in the field. Mar 27, 2025 · The era of intelligent agents is upon us, driven by revolutionary advancements in large language models. org/pdf/2404. Due to their notable capabilities in planning and reasoning, LLMs have been utilized as au-tonomous agents for the automatic execution of various tasks. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. However, accurately representing real social systems in Agent-based Modeling (ABM) is challenging due to the diverse and intricate characteristics of humans, including bounded rationality and heterogeneity. To date, LLM-based agents have been applied and shown remarkable A Survey on the Memory Mechanism of Large Language Model based Agents: Paper and Code. 07864. Jul 7, 2024 · Conclusion The paper presents a novel approach to memory sharing among large language model-based agents, which has the potential to significantly enhance the capabilities and performance of AI systems in a wide range of domains. While large language models (LLMs) have demonstrated impressive capabilities in natural language processing, existing LLM agents are typically designed for static systems and lack the A Survey on the Memory Mechanism of Large Language Model based Agents Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, Ji-Rong Wen ‪Gaoling School of Artificial Intelligence, Renmin University of China‬ - ‪‪Cited by 2,181‬‬ - ‪LLM-based Agent‬ - ‪Responsible RecSys‬ - ‪Causal Learning‬ The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al. We first discuss the construction of LLM-based autonomous agents, proposing a unified framework that encompasses much of previous work. Mar 16, 2025 · With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. Nov 24, 2024 · This article presents a comprehensive survey of large language model (LLM)-based autonomous agents, focusing on their construction, applications, and evaluation. MemGPT and Zep offer concrete implementations of 2. The memory module functions through three key operations: memory writing, which converts environmental feedback into stored content; memory management, which optimizes information through abstraction, merging, and forgetting; and memory retrieval, which extracts relevant information based on the current context to guide decision-making. It is foreseeable that in the near future, LM-driven general AI agents will serve as essential tools in production tasks, capable of autonomous communication and collaboration without human intervention. The key component to support Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. The key component to support agent-environment interactions is Mar 14, 2025 · The Rise and Potential of Large Language Model Based Agents: A Survey, arxiv [paper] 💡 A Survey on the Memory Mechanism of Large Language Model based Agents, arxiv [paper] 💡 Mar 15, 2025 · The CoALA framework provides a conceptual understanding of memory in LLM-based agents, distinguishing between working memory and long-term memory. 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 In this article, we conduct a comprehensive survey on LLM-based agents, covering their construction frameworks, application scenarios, and the exploration of societies built upon LLM-based agents. First, we introduce the conceptual architecture of LLM-based game agents, centered around six essential functional components: perception, memory, thinking, role-playing, action, and learning. Feb 10, 2025 · Bibliographic details on A Survey on the Memory Mechanism of Large Language Model based Agents. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. We also conclude some potential future directions and open problems in this flourishing field. While various memory modules have been proposed for these tasks, the impact of different memory structures across tasks remains insufficiently explored. The key component to support agent-environment interactions is Jun 9, 2025 · The memory module functions through three key operations: memory writing, which converts environmental feedback into stored content; memory management, which optimizes information through abstraction, merging, and forgetting; and memory retrieval, which extracts relevant information based on the current context to guide decision-making. A Survey on the Memory Mechanism of Large Language Model based Agents Mar 27, 2025 · Large language models have applications in various fields, including content generation, language translation, sentiment analysis, and conversational agents. 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. Contribute to AGI-Edgerunners/LLM-Agents-Papers development by creating an account on GitHub. Thus, researchers have dedicated significant effort to diverse implementations for them. This paper investigates how memory structures and memory Apr 8, 2025 · The Dawn of Intelligent Agents The artificial intelligence landscape is undergoing a revolutionary transformation. Apr 21, 2024 · Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Unlike traditional AI systems that merely respond to user inputs, these modern agents 这篇论文名为《A Survey on the Memory Mechanism of Large Language Model based Agents》，作者为Zeyu Zhang等人。论文的主要目标是对基于大型语言模型（LLM）的智能体的记忆机制进行全面的综述。随着研究和工业界对LLM智能体的兴趣增长，这种研究越发重要。 This paper provides a comprehensive overview of LLM-based game agents from a holistic viewpoint. Introduction 本知乎文章主要分为五个大的模块：第2章主要是一些背景介绍，对于搞学术的人而言，很多灵感和故事都是从一个概念的源头被启发出来的，因此我也将原文的Background部分在第1章进行了精炼。 Mar 27, 2025 · Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence. Recently, through the acquisition of vast amounts of Web knowledge, large language Sep 22, 2024 · With the rapid advancement of large models (LMs), the development of general-purpose intelligent agents powered by LMs has become a reality. It also presents agent applications, limitations and future directions of the memory mechanism. Despite the growing research interest in LLM-based agents, existing surveys primarily focus on general LLM optimization or specific agent abilities such as planning, memory, and role-playing, without treating LLM-based agent optimization as a distinct research area. Mar 22, 2024 · Recently, through the acquisition of vast amounts of Web knowledge, large language models (LLMs) have shown potential in human-level intelligence, leading to a surge in research on LLM-based TITLE：The Rise and Potential of Large Language Model Based Agents: A Survey 1. pdf https: //github. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of LLM-based autonomous agents from a holistic perspective. [abs], 2024. Aug 22, 2023 · Autonomous agents have long been a prominent research focus in both academic and industry communities. Jul 14, 2024 · 本文是LLM系列文章，针对《A Survey on the Memory Mechanism of Large Language Model based Agents》的翻译。 Jan 13, 2025 · Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. A survey on the memory mechanism of large language model based agents. Jan 21, 2024 · Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in Jul 25, 2024 · Large Language Model-Based Agents: Leveraged LLMs for reasoning, planning, and interaction, showing promise in diverse applications like software development and scientific research. The key component to support agent-environment Abstract Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Apr 15, 2024 · The adaptation of Large Language Model (LLM)-based agents to execute tasks via natural language prompts represents a significant advancement, notably eliminating the need for explicit retraining or fine tuning, but are constrained by the comprehensiveness and diversity of the provided examples, leading to outputs that often diverge significantly from expected results, especially when it comes Dec 18, 2024 · In recent years, data science agents powered by Large Language Models (LLMs), known as "data agents," have shown significant potential to transform the traditional data analysis paradigm. Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Apr 21, 2024 · The paper presents a comprehensive survey of memory mechanisms in LLM-based agents, detailing the writing, managing, and reading phases. iqjaq blgbug ddgzm nhcnh ypbuc wpn ikxypwhe ilys tdtkn tboqtsd