Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions

ACL ARR 2025 May Submission4346 Authors

Abstract:

Memory is a fundamental component of AI systems, underpinning large language models (LLMs) based agents. While prior surveys have focused on memory applications with LLMs, they often overlook the atomic operations memory dynamics.
In this survey, we first categorize memory representations into parametric and contextual forms, and then introduce six fundamental memory operations: Consolidation, Updating, Indexing, Forgetting, Retrieval, and Compression. We map these operations to the most relevant research topics across long-term, long-context, parametric modification, and multi-source memory. By reframing memory systems through the lens of atomic operations and representation types, this survey provides a structured and dynamic perspective on research, benchmark datasets, and tools related to memory in AI, clarifying the functional interplay in LLMs based agents while outlining promising directions for future research.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: memory, long-term, long-context, model editing, multi-modal, large language model

Contribution Types: Surveys

Languages Studied: English

Submission Number: 4346