From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

1. Introduction

In recent years, the rapid advancement of Large Language Models (LLMs) has fundamentally reshaped the landscape of artificial intelligence (Hurst et al. 2024, Touvron et al. 2023,Yang et al. 2025). To augment the capabilities of LLMs, researchers have developed LLM-based agents that integrate LLMs with external tools and modular components, thereby enabling planning, tool use, and environmental interaction (Luo et al. 2025,Qin et al. 2024,Yao et al. 2022). However, the inherent statelessness of LLMs poses a critical challenge: it hinders agents from maintaining logical consistency across complex, multi-step tasks and precludes learning from prior interactions, often resulting in recurring reasoning errors (Huang et al. 2023,Xiong et al. 2025). Consequently, the development of effective memory mechanisms has emerged as an architectural cornerstone. By mitigating this deficiency, memory mechanisms underpin the robust operation of LLM-based agents and pave the way for self-evolution Wang et al. (2023); Wu et al. (2025).

We identify two primary obstacles to advancing memory mechanisms for LLM agents: (i) Paradigmatic Fragmentation: Existing methodologies oscillate between two weakly integrated paradigms. One focuses on engineering, adopting design principles from operating systems for the management of memory data (Hu et al. 2024,Kang et al. 2025,Packer et al. 2023), while the other draws inspiration from cognitive science and psychology to simulate mechanisms for the formation, consolidation, and retrieval of human memory (Hou et al. 2024,Xu et al. 2025,Zhong et al. 2023). This lack of synergistic progress results in a fragmented body of research, preventing the formation of a coherent and continuous trajectory of evolution. (ii) The Absence of Technological Synthesis: Although numerous methods address isolated stages of memory processing, the field lacks a cohesive summary of the critical technologies that have historically propelled memory mechanism advancement (Xu et al. 2025,Yang et al. 2025,Zhang et al. 2025). Existing surveys have not sufficiently isolated these key technical drivers from general methodologies Cao et al. (2025); Du et al. (2025); Wu and Shu (2025); Wu et al. (2025). Consequently, the core technologies remain obscure, leaving future researchers without a clear roadmap of which innovations are robust enough to build upon.

While recent surveys have examined memory mechanisms for LLM agent systems, they lack a unified evolutionary perspective. This limitation obscures the internal drivers of memory development and impedes the in-depth exploration of architectures for next-generation agents. Specifically, Zhang et al. (2024) focuses on the classification of engineering modules, but fails to systematically expound on the logic behind critical technological transformations throughout their development. Furthermore, while Hu et al. (2025) addresses the dynamic processes of memory, its perspective remains confined to static functional categorizations, failing to reveal the underlying principles of dynamic evolution inherent to memory mechanisms.

To address these limitations, we propose a framework for memory mechanisms in LLM-based agents centered on dynamic evolution. We formalize this evolutionary process into three distinct stages: (i) Storage, which constructs diverse storage modes focused on the faithful recording of historical interaction trajectories; (ii) Reflection, which introduces a loop for dynamic evaluation to actively manage and refine these records; and (iii) Experience, which implements prospective guidance by abstracting high-level behavior patterns and strategies from clustered interactions ( Section 2).

Building upon the proposed three stages of memory mechanisms, this survey follows a "Why-How-What" logic to address three interconnected research questions: RQ1: Why do memory mechanisms evolve? reveals how the requirements for long-range consistency, dynamic environment interaction, and continual learning serve as core catalysts driving mechanistic evolution ( Section 3); RQ2: How do memory mechanisms evolve? delineates the evolutionary path from Storage to Reflection and then to Experience, analyzing the fundamental structural shifts involved ( Section 4); and RQ3: What changes does Experience bring? provides an in-depth analysis of how frontier paradigms in the Experience stage, such as proactive exploration and cross-trajectory abstraction, address the bottlenecks in agent adaptability and autonomy ( Section 5).

Finally, we outline future directions for LLM agent memory mechanisms. First, we emphasize that memory mechanisms should adopt more dynamic triggering modes based on task types ( Section 6). Second, we highlight that the construction of working memory is a vital core of memory mechanisms. Next, we advocate for the development of more comprehensive datasets for memory mechanisms, especially for the Experience stage. Finally, we establish the coordination of distributed shared memory and the fusion of multimodal memory as critical breakthroughs for future research.

The overview of this survey and related datasets is documented in Appendix A and C, respectively.

2. Background

2.1. The LLM Agent Framework

We formalize an LLM-based agent as a decision-making entity parameterized by $\theta$, interacting with a dynamic environment $\mathcal{E}$. The agent’s operation is governed by a policy ${\pi }_{\theta }$, which maps the current context to a probability distribution over the action space $\mathcal{A}$.

At time step t, the agent receives an observation $o_t\in \mathcal{O}$ and retrieves relevant information $m_t$ from its memory module $\mathcal{M}$. The generated action $a_t$ is sampled as follows:

$$a_t\sim {\pi }_{\theta }(a_t\mid \mathcal{I},o_t,m_t),$$

(1)

where $\mathcal{I}$ denotes the static system instruction, and $m_t=\mathrm{Retrieve}(\mathcal{M},o_t)$ represents the context-specific memory. Crucially, we distinguish between the global memory repository $\mathcal{M}$ and its retrieved instantiation $m_t$ at time t. In this survey, we define “LLM agent memory” $\mathcal{M}$ as an externalized repository that bridges the frozen parametric knowledge in $\theta$ and the evolving environmental dynamics.

2.2. Taxonomy

We classify the evolution of memory mechanisms into three tiers based on the level of information abstraction and cognitive processing.

Storage. Storage serves as the foundational layer. Unlike higher-level mechanisms, storage preserves trajectories with minimal transformation, maintaining a one-to-one correspondence between memory entries and execution traces. We define a trajectory $\tau$ as a chronological sequence of observation-action pairs within a task session:

$$\tau =\langle (o_1,a_1),\dots ,(o_T,a_T)\rangle .$$

(2)

The raw storage ${\mathcal{M}}_{raw}$ is formally defined as a cumulative set of historical trajectories:

$${\mathcal{M}}_{raw}={\left\{{\tau }_i\right\}}_{i=1}^N,{\tau }_i\in \mathcal{T},$$

(3)

where $\mathcal{T}$ represents the space of all possible interaction trajectories.

Reflection. Reflection is modeled as a semantic transformation mapping ${\mathcal{F}}_{ref}:\mathcal{T}\to \mathcal{S}$, where $\mathcal{S}$ denotes the space of evaluated or corrected reasoning paths. Similar to the storage phase, Reflection functions as a mechanism to populate the global repository $\mathcal{M}$, but with a focus on quality density rather than raw fidelity.

It operates by analyzing a completed trajectory ${\tau }_i$ to generate a refined memory unit $m_i^{\prime }$, which encapsulates critiques or corrective insights:

$$m_i^{\prime }={\mathcal{F}}_{ref}({\tau }_i\mid \varphi ),$$

(4)

where $\varphi$ represents the evaluation criteria. The key distinction lies in the storage protocol: while standard Storage preserves raw interaction logs, Reflection acts as a semantic filter, injecting processed insights back into the repository ($\mathcal{M}\leftarrow \mathcal{M}\cup \left\{m_i^{\prime }\right\}$). Once stored, $m_i^{\prime }$ becomes an independent memory entry, decoupling the valuable logic from the specific noise of the original trajectory ${\tau }_i$ and serving as a refined reference for future retrieval.

Experience. Experience represents the highest cognitive layer, characterized by cross-trajectory abstraction. This stage aims to satisfy the Minimum Description Length (MDL) principle by compressing redundant trajectories into generalized schemas. Let ${\mathcal{T}}_{batch}\subset {\mathcal{M}}_{raw}$ be a subset of topologically similar trajectories. We define the Experience function ${\mathcal{F}}_{exp}$ as an inductive operator that extracts a set of universally applicable rules $\mathcal{K}$:

$${\mathcal{T}}_{batch}=\{{\tau }_i\mid \mathrm{Sim}({\tau }_i,{\tau }_j)>ϵ\}.$$

(5)

$$\mathcal{K}={\mathcal{F}}_{exp}\left({\mathcal{T}}_{batch}\right)\mathrm{s}.\mathrm{t}.\left|\mathcal{K}\right|\ll \sum _{\tau \in {\mathcal{T}}_{batch}}\left|\tau \right|.$$

(6)

Formally, $\mathcal{K}$ serves as a policy prior that elevates ${\pi }_{\theta }$ beyond rule consistent actions, enabling decision-making at a higher level of abstraction than the extracted rules themselves.

Figure 1. Overview of the LLM agent Memory Mechanisms System.

Figure 1. Overview of the LLM agent Memory Mechanisms System.

3. Evolutionary Drivers

To facilitate a comprehensive understanding regarding the evolution of memory mechanisms for LLM agents, we first address the fundamental question RQ1: Why do memory mechanisms evolve? In this section, we examine three core requirements for LLM agents to investigate how they drive the progression of memory mechanisms, thereby bridging the gap between models from pretraining and the real world.

3.1. Long-Term Consistency

Consistency across long horizons constitutes a prerequisite for the deployment of LLM agents within the real world and serves as the primary impetus for the early evolution of memory mechanisms. Although large language models exhibit robust local coherence within the context window, they frequently encounter issues such as redundant exploration, accumulation of errors, and discontinuities in reasoning during interactions involving multiple steps. We analyze the necessity of consistency over long durations through two dimensions: consistency of state and consistency of goals.

Coherence of State. The inherent statelessness of LLM agents results in a deficiency of internal mechanisms for explicit anchoring, which has catalyzed the emergence of modules for memory (Huang et al. 2023,Packer et al. 2023,Sumers et al. 2023). First, these modules maintain internal states for reasoning to ensure the coherence of thought (Sun et al. 2025,Yao et al. 2023); second, they synchronize the cognition of the agent with the external world to prevent erroneous decisions arising from inaccurate internal perceptions (Majumder et al. 2023,Yang et al. 2025); finally, they internalize interactions into persistent traits of the persona to ensure uniformity in behavior (Liang et al. 2025,Park et al. 2023,Westhäußer et al. 2025).

Consistency of Goals. Due to the inherent nature of planning by the agent, LLM agents frequently optimize for actions with local consistency, which results in a departure from objectives at the global level (Everitt et al. 2025,Huang et al. 2024). Memory mechanisms mitigate this drift by providing persistent and explicit goals at a high level (Hu et al. 2024,Li et al. 2025). Furthermore, in systems with multiple agents, shared memory regarding goals can transform isolated behaviors into coordinated execution by the collective, thereby maintaining the unity of the final objective (Gao et al. 2024,Liu et al. 2025).

3.2. Dynamic Environments

The dynamic characteristics of the environment constitute a more enduring impetus for the evolution of memory mechanisms. In contrast to benchmarks of a static nature, the interplay between temporal validity and causality within the environment in settings from the real world renders fixed patterns for reasoning and static forms of storage rapidly fragile.

Figure 2. The Drivers in Dynamic Environments.

Figure 2. The Drivers in Dynamic Environments.

The Temporal Validity of Knowledge. Knowledge within environments of a dynamic nature is typically conditional rather than eternally valid (Jang et al. 2022,Ko et al. 2024,Lazaridou et al. 2021). As the environment progresses, strategies for action that were once correct may experience a gradual loss of utility. Crucially, knowledge that is outdated often fails without overt indication (Kalai and Vempala 2023,Kasai et al. 2024,Luu et al. 2022); although factually incorrect, such information may still exhibit significant relevance in its semantic representation. This necessity propels the evolution of memory mechanisms from the paradigm of static storage toward that of active management, integrating awareness of temporal factors, policies for decay, and methods for retrieval with enhanced flexibility (Du et al. 2025a,Houichime et al. 2025,Salama et al. 2025,Siyue et al. 2024,Zhong et al. 2023).

The Causal Structure of the Environment. Causal relationships within the complex real world involve delayed outcomes and cascading effects (Cui et al. 2025,Joshi et al. 2024,Liu et al. 2025). This necessitates that memory mechanisms transcend the mere documentation of interactions to construct dependencies for causality of a complex nature across steps in time (Du et al. 2025,Majumder et al. 2023,Raman et al. 2025). Consequently, planning with robustness is achieved through the realization of internal worlds characterized by consistency in causality (Bohnet et al. 2025,Kim and won Hwang 2025,Tang et al. 2024).

3.3. Continual Learning

Continual learning represents the ultimate requirement for LLM agents. Deployment within an open world inevitably involves encountering patterns that reside outside of the distribution of training. Without the effective internalization of these memories into actionable knowledge for reuse, the LLM agent will remain confined to repetitive cycles of trial and error. Therefore, memory mechanisms must not only enable the reproduction of historical trajectories but also address the bottlenecks of scaling and the requirements for abstraction inherent in dense memory.

Constraints on The Storage of Memory. Interaction with the real world over extended durations results in the linear expansion of memory in storage (Hu et al. 2023,Packer et al. 2023). Early memory mechanisms utilized techniques such as vectorization to scale storage capacity. However, recent research indicates that the unrestricted expansion of memory is detrimental to the performance of LLM agents, as errors propagate within the system for memory and contaminate the efficacy of learning (Srivastava and He 2025,Xiong et al. 2025). This necessitates the exploration of more strategic policies for the addition and deletion of information within memory mechanisms Du et al. (2025); Liu et al. (2025).

The Requirement for Experience. The memory of most LLM agents is of an episodic nature and remains restricted to specific tasks (Shinn et al. 2023,Wang et al. 2023). This limitation necessitates the transformation of raw clusters of memory into experience to provide guidance for behavior across future scenarios. Consequently, research on memory mechanisms has begun to explore various methodologies for the abstraction of experience (Alakuijala et al. 2025,Cai et al. 2025,Guo et al. 2025,Tang et al. 2025,Xia et al. 2025).

4. Evolutionary Path

Building upon these evolutionary drivers, we conduct an investigation in-depth into RQ2: How do memory mechanisms evolve? We categorize the trajectory of evolution into three primary stages: storage, reflection, and experience.

4.1. Storage

The stage of storage serves as the starting point for memory mechanisms, where the primary objective is to resolve the contradiction between the limited window of context within Large Language Models and the continuously expanding history of interaction. Memory mechanisms during this phase are dedicated to the faithful preservation of interaction trajectories ${\tau }_i$ to the greatest extent possible to maintain consistency in the actions of the agent.

Linear. Linear storage represents the most direct method of recording, in which interaction trajectories are treated as a stream of tokens ordered by time and managed typically through a strategy of first-in, first-out (FIFO). Research focuses on the extension of the window of context via modifications to the mechanism of attention or the encoding of position (Jin et al. 2024,Ratner et al. 2022,Xiao et al. 2023), as well as the achievement of information sparsification through the mechanical reduction of noise (Jiang et al. 2023,Xiao et al. 2024,Zhang et al. 2023).

Vector. Vector storage encodes interaction trajectories into a high-dimensional space, which greatly expands the capacity for the storage of memory. Such methods shift the focus of research from the design of storage toward the optimization of retrieval, including retrieval based on semantic proximity (Das et al. 2024,Liu et al. 2024,Melz 2023) as well as weighted retrieval that incorporates temporal decay and scores for importance (Park et al. 2023,Zhong et al. 2023).

Structured. Structured storage employs explicit data architectures to transcend the limitations on capacity inherent in linear storage and the ambiguity associated with vector retrieval. For instance, these methods utilize the tabular formats of relational databases for the storage of memory (Hu et al. 2023,Lee and Ko 2025,Xue et al. 2023), partition memory into distinct hierarchies to address the trade-off between storage capacity and speed of retrieval (Lu et al. 2023,Packer et al. 2023), and directly model the history of interaction as a topological network of entities and relations (Li et al. 2024,Modarressi et al. 2024).

4.2. Reflection

Mechanisms for storage fail to address the quality of memory, as raw trajectories are inevitably contaminated by hallucinations, errors in logic, and ineffective attempts. This limitation necessitates a transition of memory mechanisms toward reflection. In this phase, memory is transformed from a passive recorder into an active critic, utilizing various signals of feedback to perform correction and denoising of past trajectories to enhance the quality of the repository of memory.

Introspection. Introspective reflection conceptualizes the LLM agent as an autonomous critic that leverages the internal knowledge of the model to refine memory without the requirement for external feedback. Research in this area focuses on the correction of errors within trajectories (Bohnet et al. 2025,Liu et al. 2023,Zhang et al. 2025), the maintenance of the lifecycle of memory (Chhikara et al. 2025,Kang et al. 2025,Li et al. 2025), and the compression and distillation of long trajectories Han et al. (2025); Huang et al. (2025); Yang et al. (2025); Ye et al. (2025).

Environment. Environmental reflection treats signals from the external environment as the primary anchors for the reflection of memory to mitigate the issue of hallucinations. This approach focuses on the utilization of outcomes from the real world to proactively optimize policies for behavior (Sun et al. 2024,Yan et al. 2025) and calibrate internal models of the world (Sun et al. 2025,2024,Xiao et al. 2025).

Coordination. Collaborative reflection extends this process to the collective, leveraging the division of roles and consensus to overcome bottlenecks in the cognition of individuals. This mechanism facilitates the reflection of memory through the construction of societies of heterogeneous agents Balestri and Pescatore (2025); Bo et al. (2024); Ozer et al. (2025),Wang et al. (2025).

4.3. Experience

Although reflection effectively mitigates noise and hallucinations, reflected memories are frequently fragmented and exhibit a high degree of dependence on context. This results in significant costs for retrieval and a heavy burden of inference for memory mechanisms when addressing new tasks. Moreover, recent research indicates that LLM agents often demonstrate a pronounced tendency to follow successful trajectories; corrected trajectories devoid of abstraction may still induce errors resulting from minor shifts in context. Consequently, memory in the stage of experience extracts universal heuristic wisdom by isolating similar trajectories from their specific contexts. This approach simultaneously compresses the originally vast repository of memory and enables a capacity for generalization to unknown environments through a form of intuition similar to that of humans.

Explicit. Explicit experience represents the integration of symbols, extracting human-readable and editable experiences with a high level of generalizability from clusters of interaction trajectories. This allows the LLM agent to achieve a highly interpretable process of self-evolution by either concretizing experiences into natural language policies (Cai et al. 2025,Hassell et al. 2025,Wan et al. 2025,Zhang et al. 2025) or directly abstracting them into executable entities (Shi et al. 2025,Wang et al. 2025,Zhang et al. 2025).

Implicit. Implicit experience internalizes interaction histories into model parameters, aiming to resolve the inference overhead and context limitations inherent in explicit memory. Implicit experience can be realized by directly converting experiences into the model’s intrinsic capabilities through fine-tuning (Alakuijala et al. 2025,Tandon et al. 2025,Yu et al. 2025,Zhai et al. 2025,Zhang et al. 2025). Furthermore, the research community is exploring the transformation of experience into latent variables within the model’s hidden layers, which are then dynamically invoked during the inference process (Zhang et al. 2025,?).

Hybrid. Hybrid experience establishes a dynamic cycle of accumulation and internalization. Through a mechanism for experience transfer, explicit experience is treated as a high-capacity cache, which is subsequently compressed and internalized into the implicit weights of the model through periodic updates of parameters (Anonymous 2025,Ouyang et al. 2025,Wu et al. 2025).

5. Transformative Experience

Following the exposition of the evolutionary trajectory for memory mechanisms, we address RQ3: What changes does Experience bring? In this section, we elucidate the distinct technical characteristics of experience as a novel stage in the development of memory mechanisms.

5.1. Active Exploration

Active exploration leverages memory mechanisms to transform LLM agents from passive recorders of information into collectors of experience driven by goals. In the stage of Experience, the core capability of memory mechanisms is no longer confined to the storage of history, but extends to the acquisition of valuable experience through the active exploration of the environment.

Exploration Mechanisms. The driving mechanisms for active exploration have transitioned from traditional strategies of random exploration toward more profound drivers of intrinsic motivation and feedback. Drivers based on signals of reward guide LLM agents to explore state spaces of greater value through the design and optimization of immediate reward functions (Pan et al. 2025,Sun et al. 2025,Zheng et al. 2024); drivers based on curricula facilitate exploration tasks of increasing difficulty through the dynamic generation and adjustment of sequences for tasks (Ahn et al. 2022,Wei et al. 2025); and drivers based on reuse enable exploration of high efficiency through the abstraction and reuse of trajectories from history (Cai et al. 2025,Wang et al. 2025).

Exploration Dimensions. The core of active exploration resides in the utilization of memory mechanisms to facilitate the expansion of the boundaries of capability for LLM agents. This process can be categorized into three critical dimensions: exploration of breadth aims to alleviate cognitive deficiencies of LLM agents in unfamiliar environments, transforming memory into experience that is structured through mechanisms of curiosity (Cheng et al. 2025,Qi et al. 2025,Zhai et al. 2025); exploration of depth focuses on the extraction of skills of a high order within vertical tasks, driving the evolution of memory from the basic following of instructions to complex experiential strategies (Liu et al. 2025,Xia et al. 2025); and exploration of strategy centers on the dynamic optimization of paths for decision making, leveraging the accumulation of experience to enhance the precision of decisions for LLM agents during planning over long horizons Bidochko and Vyklyuk (2026),Shi et al. (2025).

5.2. Cross-Trajectory Abstraction

Cross-trajectory abstraction compresses isolated trajectories into universal patterns, transforming scattered and episodic experiences into stable priors for policy. This enables LLM agents to transcend specific sequences of actions and engage in decision making at higher dimensions of abstraction, which provides prospective guidance for tasks that are unknown and facilitates an understanding of underlying regularities.

Figure 3. Overview of Cross-Trajectory Abstraction.

Figure 3. Overview of Cross-Trajectory Abstraction.

Abstraction Mechanisms. The mechanism for abstraction serves as the core operator for the transformation of groups of raw interaction trajectories into experience that is universal. In contrast to mechanisms for reflection that focus on the correction of errors within single trajectories, abstraction during the stage of experience emphasizes the execution of inductive operations across trajectories. According to its operational logic, this process includes contrastive induction, which utilizes the opposition between successful and failed trajectories to delineate the boundaries of policy with precision (Forouzandeh et al. 2025,He et al. 2024); the distillation of actions of fine granularity into patterns of thought of a high order through the chunking and aggregation of behavioral sequences across multiple levels of granularity (Fang et al. 2025,Latimer et al. 2025); the encapsulation of recurring patterns of behavior into program functions that are reusable by leveraging the compositionality of code (Wang et al. 2025,Yang et al. 2025,Zhang et al. 2025); and the internalization of groups of trajectories into the parameters of the model through techniques for fine-tuning (Chen et al. 2025,Ding et al. 2025).

Abstraction Granularity. The hierarchy of abstraction for memory mechanisms determines the boundaries for generalization and the degree of interpretability for experience. Based on the degree to which the results of abstraction deviate from original trajectories, these can be categorized into three progressive levels: abstraction at the shallow level retains a portion of semantic logic, utilizing “rules” described in natural language as experience (Cao et al. 2025,Chen et al. 2025,Hayashi et al. 2025,Wei et al. 2025); abstraction at the intermediate level completely removes redundancies of natural language, extracting only modular skeletons for execution as experience (Liu et al. 2025,Wang et al. 2024,Yu et al. 2025); and abstraction at the deep level compresses the distribution of trajectories into the weights of the model, enabling the complete transformation of experience into intuition for decision making (Cheng et al. 2025,Luo et al. 2025,Wang et al. 2025).

6. Future Directions

In this section, we discuss emerging prospects and promising directions for memory mechanisms for LLM agents.

Active Memory Perception. Currently, certain memory mechanisms still utilize modes of passive triggering, which necessitates that LLM agents perform the indiscriminate retrieval of a significant portion of the repository of memory (Rasmussen et al. 2025,Wang et al. 2025). More importantly, the persistent retrieval of irrelevant or obsolete memories can disrupt the coherence in reasoning of the LLM agent Tan et al. (2025); Xu et al. (2025). Recent work has begun to address this challenge through autonomous retrieval controllers (Du et al. 2025b). Future research demands that memory mechanisms autonomously evaluate whether a task requires the introduction of additional memory and determine the specific type of memory to be integrated, ensuring that memory mechanisms function as resources that are invoked on demand.

Organization of Working Memory. As the complexity of tasks and the horizons encountered by LLM agents continue to expand, the construction of working memory within tasks has emerged as a primary bottleneck. LLM agents must reconstruct trajectories from the past into memory intervals that are dynamic and plastic to facilitate the effective allocation of attention (Hu et al. 2024,Luo et al. 2025). Future research may focus on the isolation of interval memory, the retrospective integration of critical nodes for decision making, and the adaptive pruning of working memory (Nan et al. 2025,Sun et al. 2025,Zhang et al. 2025).

Benchmark for Experience. Existing datasets primarily evaluate the capacity for retrieval and denoising of memory within the stages of storage and reflection, whereas the evaluation of the capacity for abstraction and generalization during the stage of experience remains significantly insufficient (Appendix C). The assessment of the lifecycle of experience is closely linked to the capacity for meta-learning in LLM agents, which is essential for the realization of systems for self evolution based on active generalization (Behrouz et al. 2024,Wei et al. 2025). Consequently, the path of evolution we propose provides a valuable foundation for guiding the development of these benchmarks.

Distributed Shared Memory. Collaboration among multiple agents represents the essential pathway toward the realization of “Organizations.” This establishes distributed shared memory as central to current research Wu et al. (2025). At present, mechanisms for shared memory rely primarily on communication through explicit dialogue, which is not only constrained by bottlenecks in bandwidth but is also prone to the introduction of noise during the process of exchange (Liao et al. 2025,Tran et al. 2025,Zou et al. 2025). To overcome current communication constraints, future efforts should prioritize the development of consensus memory systems. These systems aim to achieve efficient synchronization between individual perspectives and collective knowledge, thereby fostering a more agile process of socialized experience evolution (Rezazadeh et al. 2025,Yuen et al. 2025).

Multimodal Memory. Multimodal memory represents a significant direction for the future development of memory mechanisms for LLM agents. This direction requires the integration of states of visual perception, processes of linguistic reasoning, and other perceptual modalities into memory units characterized by unified temporality and semantics (He et al. 2025,Liu et al. 2025,Zhou et al. 2025). For embodied intelligence in particular, the integrity of internal models of the world directly influences the planning and execution of tasks (Feng et al. 2025,Long et al. 2025). To achieve this objective, existing research explores novel memory mechanisms by investigating multimodal abstraction, temporal alignment across modalities, and the efficient consolidation of memory.

7. Conclusion

This survey provides a systematic review of memory mechanisms for LLM agents, establishing an evolutionary framework that encompasses three progressive stages: storage, reflection, and experience. Our analysis demonstrates that memory evolution is not merely the expansion of storage capacity but fundamentally involves the enhancement of information density and a transformation across cognitive abstraction dimensions. By introducing mechanisms such as active exploration and cross-trajectory abstraction, memory mechanisms within the experience stage enable agents to transcend situational constraints and acquire transferable behavioral experience. We hope this survey assists the community in designing more advanced memory mechanisms, guiding LLM agents toward the realization of true general artificial intelligence.