mlsanityData to 14 Oct 2026

Empowering Working Memory for Large Language Model Agents

arXiv 2312.17259 ↗First posted 22 Dec 2023cs.CL cs.AIcited by 18

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions, hindering complex reasoning. This paper explores the potential of applying cognitive psychology's working memory frameworks, to enhance LLM architecture. The limitations of traditional LLM memory designs are analyzed, including their isolation of distinct dialog episodes and lack of persistent memory links. To address this, an innovative model is proposed incorporating a centralized Working Memory Hub and Episodic Buffer access to retain memories across episodes. This architecture aims to provide greater continuity for nuanced contextual reasoning during intricate tasks and collaborative scenarios. While promising, further research is required into optimizing episodic memory encoding, storage, prioritization, retrieval, and security. Overall, this paper provides a strategic blueprint for developing LLM agents with more sophisticated, human-like memory capabilities, highlighting memory mechanisms as a vital frontier in artificial general intelligence.

Key facts. Cited by 18 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 5 of its 11 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

5 of 11 references.

References · 5

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Augmenting Language Models with Long-Term Memorycited by 189
  3. 2023PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Trainingcited by 111
  4. 2023RecurrentGPT: Interactive Generation of (Arbitrarily) Long Textcited by 84
  5. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 13; 2026: 2.

18 papers.

Sort:

By area:

  1. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 186
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 169
  3. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  4. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  5. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 31
  6. 2025Cognitive Memory in Large Language Modelscited by 29
  7. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 29
  8. 2024Symbolic Working Memory Enhances Language Models for Complex Rule Applicationcited by 17
  9. 2025Agentic AI Frameworks: Architectures, Protocols, and Design Challengescited by 16
  10. 2025Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integrationcited by 12
  11. 2025On the Failure of Latent State Persistence in Large Language Modelscited by 9
  12. 2025MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Servicecited by 7
6 more
  1. 2024Towards Agentic AI on Particle Acceleratorscited by 5
  2. 2025ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challengescited by 5
  3. 2026Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agentscited by 3
  4. 2025Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrievalcited by 0
  5. 2025CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applicationscited by 0
  6. 2026Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  2. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  3. 2024On the Structural Memory of LLM Agents
  4. 2026Understanding Large Language Models
  5. 2025Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents
  6. 2023Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory
  7. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  8. 2025Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents