# CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents

arXiv: https://arxiv.org/abs/2505.13044 · HTML: https://mlsanity.com/paper/2505.13044/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 72 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Detecting and Preventing Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2308.06394/) (2023)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [Long Time No See! Open-Domain Conversation with Long-Term Persona Memory](https://mlsanity.com/paper/2203.05797/) (2022)
- [Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation](https://mlsanity.com/paper/2404.05970/) (2024)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Keep Me Updated! Memory Management in Long-term Conversations](https://mlsanity.com/paper/2210.08750/) (2022)
- [Prompted LLMs as Chatbot Modules for Long Open-domain Conversation](https://mlsanity.com/paper/2305.04533/) (2023)
- [Design Principles for Generative AI Applications](https://mlsanity.com/paper/2401.14484/) (2024)
- [A Practical Survey on Zero-shot Prompt Design for In-context Learning](https://mlsanity.com/paper/2309.13205/) (2023)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey](https://mlsanity.com/paper/2401.07872/) (2024)
- [Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems](https://mlsanity.com/paper/2501.10332/) (2025)
- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [Can A Cognitive Architecture Fundamentally Enhance LLMs? Or Vice Versa?](https://mlsanity.com/paper/2401.10444/) (2024)
- [CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding](https://mlsanity.com/paper/2501.09645/) (2025)
- [To Reuse or Not To Reuse? A Framework and System for Evaluating Summarized Knowledge](https://mlsanity.com/paper/2102.06231/) (2021)
- [Knowledge Tagging with Large Language Model based Multi-Agent System](https://mlsanity.com/paper/2409.08406/) (2024)
- [Does Your AI Agent Get You? A Personalizable Framework for Approximating Human Models from Argumentation-based Dialogue Traces](https://mlsanity.com/paper/2502.16376/) (2025)

## Built on by (most cited first, 7 of 7)

- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning](https://mlsanity.com/paper/2511.08301/) (2025)
- [FileGram: Grounding Agent Personalization in File-System Behavioral Traces](https://mlsanity.com/paper/2604.04901/) (2026)
- [AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems](https://mlsanity.com/paper/2609.12320/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user as well as contextual knowledge and understanding of the ever-changing environment. To overcome these challenges, holistic memory modeling is required to efficiently retrieve and store relevant information across interaction sessions for suitable responses. Cognitive AI, which aims to simulate the human thought process in a computerized model, highlights interesting aspects, such as thoughts, memory mechanisms, and decision-making, that can contribute towards improved memory modeling for LLMs. Inspired by these cognitive AI principles, we propose our memory framework CAIM. CAIM consists of three modules: 1.) The Memory Controller as the central decision unit; 2.) the Memory Retrieval, which filters relevant data for interaction upon request; and 3.) the Post-Thinking, which maintains the memory storage. We compare CAIM against existing approaches, focusing on metrics such as retrieval accuracy, response correctness, contextual coherence, and memory storage. The results demonstrate that CAIM outperforms baseline frameworks across different metrics, highlighting its context-awareness and potential to improve long-term human-AI interactions.