mlsanityData to 7 Oct 2026

MiA-Signature: Approximating Global Activation for Long-Context Understanding

arXiv 2605.06416 ↗First posted 7 May 2026cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

A growing body of work in cognitive science suggests that reportable conscious access is associated with global ignition over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of Mindscape Activation Signature (MiA-Signature), a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

20 of 33 references.

References · 20

  1. 2024GPT-4o System Cardcited by 4,467
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  3. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  5. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  6. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  7. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  8. 2023Active Retrieval Augmented Generationcited by 506
  9. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  10. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  11. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 235
  12. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 140
8 more
  1. 2024One Thousand and One Pairs: A "novel" challenge for long-context language modelscited by 80
  2. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Modelscited by 37
  3. 2025Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agentscited by 37
  4. 2024DetectiveQA: Evaluating Long-Context Reasoning on Detective Novelscited by 21
  5. 2025ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoningcited by 13
  6. 2025NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contextscited by 8
  7. 2026Query-focused and Memory-aware Reranker for Long Context Processingcited by 6
  8. 2025Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understandingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026A New Role for Relevance: Guiding Corpus Interaction in Agentic Searchcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2026Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
  2. 2024Controlling Large Language Model Agents with Entropic Activation Steering
  3. 2025Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
  4. 2025Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
  5. 2026ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning
  6. 2025Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
  7. 2026LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation
  8. 2025Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning