mlsanityData to 14 Oct 2026

Cognitive Workspace: Active Memory Management for LLMs -- An Empirical Study of Functional Infinite Context

arXiv 2508.13171 ↗First posted 8 Aug 2025cs.AI cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) face fundamental limitations in context management despite recent advances extending context windows to millions of tokens. We propose Cognitive Workspace, a novel paradigm that transcends traditional Retrieval-Augmented Generation (RAG) by emulating human cognitive mechanisms of external memory use. Drawing from cognitive science foundations including Baddeley's working memory model, Clark's extended mind thesis, and Hutchins' distributed cognition framework, we demonstrate that current passive retrieval systems fail to capture the dynamic, task-driven nature of human memory management. Our analysis of 2024-2025 developments reveals that while techniques like Infini-attention and StreamingLLM achieve impressive context lengths, they lack the metacognitive awareness and active planning capabilities essential for true cognitive extension. Cognitive Workspace addresses these limitations through three core innovations: (1) active memory management with deliberate information curation, (2) hierarchical cognitive buffers enabling persistent working states, and (3) task-driven context optimization that dynamically adapts to cognitive demands. Empirical validation demonstrates Cognitive Workspace achieves an average 58.6% memory reuse rate (ranging from 54-60% across different tasks) compared to 0% for traditional RAG, with 17-18% net efficiency gain despite 3.3x higher operation counts. Statistical analysis confirms these advantages with p < 0.001 and Cohen's d > 23 across multiple task types, establishing the first quantitative evidence for active memory superiority in LLM systems. We present a comprehensive theoretical framework synthesizing insights from 50+ recent papers, positioning Cognitive Workspace as a fundamental shift from information retrieval to genuine cognitive augmentation.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 23 of its 51 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

23 of 51 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  11. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  12. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
11 more
  1. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  2. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  4. 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attentioncited by 407
  5. 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attentioncited by 383
  6. 2024Mixture-of-Depths: Dynamically allocating compute in transformer-based language modelscited by 258
  7. 2022Memorizing Transformerscited by 226
  8. 2024Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentioncited by 200
  9. 2024Corrective Retrieval Augmented Generationcited by 197
  10. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151
  11. 2025Cost-Awareness in Tree-Search LLM Planning: A Systematic Studycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMscited by 1
  2. 2026Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systemscited by 1
  3. 2026The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Empowering Working Memory for Large Language Model Agents
  2. 2026Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models
  3. 2025Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
  4. 2026LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
  5. 2025CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents
  6. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
  7. 2026Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
  8. 2026Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory