mlsanityData to 14 Oct 2026

From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models

arXiv 2601.15690 ↗First posted 22 Jan 2026cs.AI stat.APcited by 2

Not on the map. Why?

Abstract (arXiv)

While Large Language Models (LLMs) show remarkable capabilities, their unreliability remains a critical barrier to deployment in high-stakes domains. This survey charts a functional evolution in addressing this challenge: the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior. We demonstrate how uncertainty is leveraged as an active control signal across three frontiers: in advanced reasoning to optimize computation and trigger self-correction; in autonomous agents to govern metacognitive decisions about tool use and information seeking; and in reinforcement learning to mitigate reward hacking and enable self-improvement via intrinsic rewards. By grounding these advancements in emerging theoretical frameworks like Bayesian methods and Conformal Prediction, we provide a unified perspective on this transformative trend. This survey provides a comprehensive overview, critical analysis, and practical design patterns, arguing that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 78 references that are in the map. First posted on arXiv 22 Jan 2026.

Builds on

51 of 78 references.

References · 51

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2023Let's Verify Step by Stepcited by 3,789
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  6. 2025s1: Simple test-time scalingcited by 1,341
  7. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  8. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  9. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  10. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMscited by 249
  11. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  12. 2025Learning to Reason without External Rewardscited by 210
38 more
  1. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 166
  2. 2024AlphaMath Almost Zero: Process Supervision without Processcited by 162
  3. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scalingcited by 136
  4. 2025Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivizationcited by 128
  5. 2025Confidence Improves Self-Consistency in LLMscited by 113
  6. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  7. 2024Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervisioncited by 96
  8. 2024Large language model validity via enhanced conformal prediction methodscited by 92
  9. 2025Tell me about yourself: LLMs are aware of their learned behaviorscited by 91
  10. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 90
  11. 2025Reward Shaping to Mitigate Reward Hacking in RLHFcited by 88
  12. 2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknowncited by 74
  13. 2024API Is Enough: Conformal Prediction for Large Language Models Without Logit-Accesscited by 69
  14. 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guaranteescited by 65
  15. 2024A Survey of Uncertainty Estimation in LLMs: Theory Meets Practicecited by 55
  16. 2022Language Models in the Loop: Incorporating Prompting into Weak Supervisioncited by 52
  17. 2025SMART: Self-Aware Agent for Tool Overuse Mitigationcited by 52
  18. 2025Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoningcited by 51
  19. 2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agentscited by 46
  20. 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 42
  21. 2025Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoningcited by 36
  22. 2024Bayesian Reward Models for LLM Alignmentcited by 35
  23. 2025THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Modelscited by 35
  24. 2025Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topologycited by 25
  25. 2025AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidencecited by 24
  26. 2020Modern Monte Carlo Methods for Efficient Uncertainty Quantification and Propagation: A Surveycited by 21
  27. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
  28. 2025CER: Confidence Enhanced Reasoning in LLMscited by 17
  29. 2024Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuningcited by 16
  30. 2025Accelerating Large Language Model Reasoning via Speculative Searchcited by 16
  31. 2025Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMscited by 16
  32. 2025Post-Training Large Language Models via Reinforcement Learning from Self-Feedbackcited by 15
  33. 2024SAUP: Situation Awareness Uncertainty Propagation on LLM Agentcited by 14
  34. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13
  35. 2025CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoningcited by 12
  36. 2025Do not Abstain! Identify and Solve the Uncertaintycited by 11
  37. 2025Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoningcited by 10
  38. 2024Resistance Against Manipulative AI: key factors and possible actionscited by 9

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 9
  2. 2026Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gapscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards
  2. 2026It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
  3. 2026From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
  4. 2024Controlling Large Language Model Agents with Entropic Activation Steering
  5. 2026Agentic Control in Variational Language Models
  6. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
  7. 2026Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
  8. 2026U-Space: Uncovering When and Why Uncertainty Arises in Language Models