Skip to content

Learning to Remember: Advances in Memory Mechanisms for Large Language Models

Oct 2026 · Vicinagearth. · 0 citations · 208 references
Computer Science

TL;DR

This survey organizes the literature around three complementary dimensions: the life cycle of memory, the storage substrate, and the system role that memory plays in LLM-based agents, while using cognitive-science-inspired memory concepts as a lightweight conceptual motivation rather than as a separate technical contribution or implementation family.

Abstract

Memory has become a central mechanism for extending large language models (LLMs) beyond fixed context windows, stateless interaction, and static parametric knowledge. This survey organizes the literature around three complementary dimensions: the life cycle of memory, the storage substrate, and the system role that memory plays in LLM-based agents, while using cognitive-science-inspired memory concepts as a lightweight conceptual motivation rather than as a separate technical contribution or implementation family. On this basis, we distinguish three mechanism families: nonparametric memory, where information is stored outside model parameters in text, graph, multimodal, or database-like structures; parametric memory, where information is stored or accessed through activations, key-value caches, learned modules, adapter-based parameterizations, or model weights; and memory for agent evolution, where stored experiences support reinforcement learning, continual learning, procedural reuse, context engineering, and agent harness design. Evaluation is treated as a separate cross-cutting component rather than as a memory mechanism. Unlike surveys that focus primarily on retrieval-augmented generation or long-context modeling, this paper emphasizes the full memory life cycle: construction, maintenance, retrieval, consolidation, forgetting, governance, and evaluation. By aligning conceptual motivations, computational memory mechanisms, benchmarks, and deployment concerns, the survey provides a structured roadmap for designing memory-augmented LLM agents that are persistent, adaptive, auditable, and safe to update over time.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning

This work introduces a unified formulation of context optimization and shows that an agent memory system update can be interpreted as an optimization update procedure over the model's context, and proposes GraphMemory, a lightweight graph-based memory that accumulates, refines, organizes, and connects reusable strategi...

Yehya Farhat, Michael Desmond, Anastasios Kyrillidis · 0 citations
Preprint Oct 2026

Mixture-of-Memories: Low-Overhead Language Modeling with Modular Knowledge Injection

Large language models store substantial factual knowledge in their parameters, yet this knowledge is difficult to control, update, and reliably elicit at inference time. Existing memory-augmented approaches typically rely on a single auxiliary mechanism, such as retrieval, parameter updates, or neural memory, and there...

Yifan Lu, Ru-Bin Wei, Zi-Yun Zou et al. · 0 citations
#natural language process... Preprint Oct 2026

Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing

External-memory systems extend language-model applications beyond a context window, but their quality depends critically on the model executing the write path: deciding what to retain, how precisely to represent it, and how new evidence should update persistent state. Existing frameworks typically place a general-purpo...

Tian-Xiang Fei, Jia-Zheng Kang, Mao Zheng et al. · 0 citations

GenMem: Generative Symbolic Memory for Self-Evolving Harness

GenMem is presented, which reformulates memory management as generative symbolic addressing, a multi-level discrete token tuple drawn from a Cartesian-product address space that factorizes a million-scale sparse memory space using fewer than one hundred discrete symbols.

Xin-Ke Jiang, Tao Feng, Wei-Xuan Xu et al. · 0 citations
Preprint Oct 2026

Memory-Centric Continual Learning for AI Agents

Autonomous agents powered by foundation models can reason, plan, and use tools, but their fixed weights and context limits hinder sustained learning from experience over long-term deployment. While external memory systems attempt to bridge this gap, they mostly act as passive retrieval caches, evaluated primarily by wh...

Dongfang Li, Zhuo-En Chen, Bo-Nian Jia et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.