From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

• URL: http://arxiv.org/abs/2504.15965v2
• Date: Wed, 23 Apr 2025 13:47:27 GMT
• Title: From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
• Authors: Yaxiong Wu, Sheng Liang, Chen Zhang, Yichao Wang, Yongyue Zhang, Huifeng Guo, Ruiming Tang, Yong Liu,
• Abstract summary: Memory is the process of encoding, storing, and retrieving information.<n>In the era of large language models (LLMs), memory refers to the ability of an AI system to retain, recall, and use information from past interactions to improve future responses and interactions.
• Score: 34.361000444808454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It plays a crucial role in shaping our identity, making decisions, learning from past experiences, building relationships, and adapting to changes. In the era of large language models (LLMs), memory refers to the ability of an AI system to retain, recall, and use information from past interactions to improve future responses and interactions. Although previous research and reviews have provided detailed descriptions of memory mechanisms, there is still a lack of a systematic review that summarizes and analyzes the relationship between the memory of LLM-driven AI systems and human memory, as well as how we can be inspired by human memory to construct more powerful memory systems. To achieve this, in this paper, we propose a comprehensive survey on the memory of LLM-driven AI systems. In particular, we first conduct a detailed analysis of the categories of human memory and relate them to the memory of AI systems. Second, we systematically organize existing memory-related work and propose a categorization method based on three dimensions (object, form, and time) and eight quadrants. Finally, we illustrate some open problems regarding the memory of current AI systems and outline possible future directions for memory in the era of large language models.

Related papers

• Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions [55.19217798774033]
  Memory is a fundamental component of AI systems, underpinning large language models (LLMs) based agents. We introduce six fundamental memory operations: Consolidation, Updating, Indexing, Forgetting, Retrieval, and Compression. This survey provides a structured and dynamic perspective on research, benchmark datasets, and tools related to memory in AI.
  arXiv  Detail & Related papers  (2025-05-01T17:31:33Z)
• Memorization and Knowledge Injection in Gated LLMs [8.305942415868042]
  Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge. Memory Embedded in Gated LLMs (MEGa) injects event memories directly into the weights of LLMs. During inference, a gating mechanism activates relevant memory weights by matching query embeddings to stored memory embeddings.
  arXiv  Detail & Related papers  (2025-04-30T00:28:32Z)
• MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation [15.64077949677469]
  We present a novel Memory-Augmented Dialogue Benchmark (MADail-Bench) to evaluate the effectiveness of memory-augmented dialogue systems (MADS) The benchmark assesses two tasks separately: memory retrieval and memory recognition with the incorporation of both passive and proactive memory recall data. Results from cutting-edge embedding models and large language models on this benchmark indicate the potential for further advancement.
  arXiv  Detail & Related papers  (2024-09-23T17:38:41Z)
• Survey on Memory-Augmented Neural Networks: Cognitive Insights to AI Applications [4.9008611361629955]
  Memory-Augmented Neural Networks (MANNs) blend human-like memory processes into AI. The study investigates advanced architectures such as Hopfield Networks, Neural Turing Machines, Correlation Matrix Memories, Memformer, and Neural Attention Memory. It dives into real-world uses of MANNs across Natural Language Processing, Computer Vision, Multimodal Learning, and Retrieval Models.
  arXiv  Detail & Related papers  (2023-12-11T06:05:09Z)
• A Framework for Inference Inspired by Human Memory Mechanisms [9.408704431898279]
  We propose a PMI framework that consists of perception, memory and inference components. The memory module comprises working and long-term memory, with the latter endowed with a higher-order structure to retain extensive and complex relational knowledge and experience. We apply our PMI to improve prevailing Transformers and CNN models on question-answering tasks like bAbI-20k and Sort-of-CLEVR datasets.
  arXiv  Detail & Related papers  (2023-10-01T08:12:55Z)
• Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models [49.39276272693035]
  Large-scale pre-trained language models have shown remarkable memorizing ability. Vanilla neural networks without pre-training have been long observed suffering from the catastrophic forgetting problem. We find that 1) Vanilla language models are forgetful; 2) Pre-training leads to retentive language models; 3) Knowledge relevance and diversification significantly influence the memory formation.
  arXiv  Detail & Related papers  (2023-05-16T03:50:38Z)
• LLM as A Robotic Brain: Unifying Egocentric Memory and Control [77.0899374628474]
  Embodied AI focuses on the study and development of intelligent systems that possess a physical or virtual embodiment (i.e. robots) Memory and control are the two essential parts of an embodied system and usually require separate frameworks to model each of them. We propose a novel framework called LLM-Brain: using Large-scale Language Model as a robotic brain to unify egocentric memory and control.
  arXiv  Detail & Related papers  (2023-04-19T00:08:48Z)
• Memory-Augmented Theory of Mind Network [59.9781556714202]
  Social reasoning requires the capacity of theory of mind (ToM) to contextualise and attribute mental states to others. Recent machine learning approaches to ToM have demonstrated that we can train the observer to read the past and present behaviours of other agents. We tackle the challenges by equipping the observer with novel neural memory mechanisms to encode, and hierarchical attention to selectively retrieve information about others. This results in ToMMY, a theory of mind model that learns to reason while making little assumptions about the underlying mental processes.
  arXiv  Detail & Related papers  (2023-01-17T14:48:58Z)
• A Machine with Short-Term, Episodic, and Semantic Memory Systems [9.42475956340287]
  Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.
  arXiv  Detail & Related papers  (2022-12-05T08:34:23Z)
• Memory and attention in deep learning [19.70919701635945]
  Memory construction for machine is inevitable. Recent progresses on modeling memory in deep learning have revolved around external memory constructions. The aim of this thesis is to advance the understanding on memory and attention in deep learning.
  arXiv  Detail & Related papers  (2021-07-03T09:21:13Z)
• Self-Attentive Associative Memory [69.40038844695917]
  We propose to separate the storage of individual experiences (item memory) and their occurring relationships (relational memory) We achieve competitive results with our proposed two-memory model in a diversity of machine learning tasks.
  arXiv  Detail & Related papers  (2020-02-10T03:27:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.