mlsanityData to 14 Oct 2026

A Scenario-Driven Cognitive Approach to Next-Generation AI Memory

arXiv 2509.13235 ↗First posted 16 Sep 2025cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

As artificial intelligence advances toward artificial general intelligence (AGI), the need for robust and human-like memory systems has become increasingly evident. Current memory architectures often suffer from limited adaptability, insufficient multimodal integration, and an inability to support continuous learning. To address these limitations, we propose a scenario-driven methodology that extracts essential functional requirements from representative cognitive scenarios, leading to a unified set of design principles for next-generation AI memory systems. Based on this approach, we introduce the COgnitive Layered Memory Architecture (COLMA), a novel framework that integrates cognitive scenarios, memory processes, and storage mechanisms into a cohesive design. COLMA provides a structured foundation for developing AI systems capable of lifelong learning and human-like reasoning, thereby contributing to the pragmatic development of AGI.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 116 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

26 of 116 references.

References · 26

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2023A Survey of Large Language Modelscited by 2,576
  3. 2017Billion-scale similarity search with GPUscited by 2,497
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  6. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  8. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  9. 2018Experience Replay for Continual Learningcited by 1,095
  10. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  11. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,013
  12. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
14 more
  1. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  2. 2020Knowledge Graphscited by 621
  3. 2013Challenges in Representation Learning: A report on three machine learning contestscited by 302
  4. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
  5. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  6. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 173
  7. 2025Memp: Exploring Agent Procedural Memorycited by 103
  8. 2021Relating transformers to models and neural representations of the hippocampal formationcited by 62
  9. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  10. 2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAIcited by 35
  11. 2024Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Modelscited by 28
  12. 2025Key-value memory in the braincited by 24
  13. 2025HAWK: A Hierarchical Workflow Framework for Multi-Agent Collaborationcited by 4
  14. 2023Self-recovery of memory via generative replaycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 55
  2. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  3. 2025Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligencecited by 2