mlsanityData to 7 Oct 2026

Lost in Context: Addressing Context Anxiety in Large Language Models

arXiv 2607.21616 ↗First posted 29 May 2026cs.AIcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Conventional wisdom suggests that reasoning models fail when problems exceed their capabilities. However, we find that frontier reasoning models sometimes possess the necessary capabilities to solve problems but fail due to premature self-doubt -- a phenomenon informally known as context anxiety. We provide the first systematic study of context anxiety, demonstrating that it arises, in part, from a model's inability to accurately estimate the tokens required to complete a task. We also show that context anxiety leads to material efficiency losses when models operate under perceived constraints. Building on this analysis, we further show that models can learn alternative strategies for solving long-horizon problems without exhibiting context anxiety, suggesting that performance improvements may be achievable not through scaling model capabilities, but by improving models' ability to accurately assess and adapt to their own limitations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 28 of its 33 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

28 of 33 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs30 Apr
  2. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  3. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning25 Feb
  4. 2023Making Large Language Models Better Reasoners with Alignment5 Sep
  5. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 23

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2022Emergent Abilities of Large Language Modelscited by 2,483
  6. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  7. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  8. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  9. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  10. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  11. 2022Large Language Models Are Reasoning Teacherscited by 318
  12. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
11 more
  1. 2022Emergent Analogical Reasoning in Large Language Modelscited by 239
  2. 2023Do Large Language Models Know What They Don't Know?cited by 238
  3. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  4. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 221
  5. 2024Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Modelscited by 150
  6. 2023Are Emergent Abilities in Large Language Models just In-Context Learning?cited by 109
  7. 2024Large Language Models Must Be Taught to Know What They Don't Knowcited by 99
  8. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 91
  9. 2024What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineeringcited by 88
  10. 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipelinecited by 86
  11. 2025Emergent Abilities in Large Language Models: A Surveycited by 34

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning Shift: How Context Silently Shortens LLM Reasoning
  2. 2025The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
  3. 2026Contextual Drag: How Errors in the Context Affect LLM Reasoning
  4. 2025Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
  5. 2025Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling
  6. 2026The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents
  7. 2026In-Context Environments Induce Evaluation-Awareness in Language Models
  8. 2026When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling