mlsanityData to 14 Oct 2026

MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models

arXiv 2511.06419 ↗First posted 9 Nov 2025cs.AI cs.CLcited by 12

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

Abstract (arXiv)

Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent reasoning. This behavior undermines model reliability and poses societal risks. Mitigating LRM sycophancy requires monitoring how this sycophancy emerges during the reasoning trajectory; however, current methods mainly focus on judging based on final answers and correcting them, without understanding how sycophancy develops during reasoning processes. To address this limitation, we propose MONICA, a novel Monitor-guided Calibration framework that monitors and mitigates sycophancy during model inference at the level of reasoning steps, without requiring the model to finish generating its complete answer. MONICA integrates a sycophantic monitor that provides real-time monitoring of sycophantic drift scores during response generation with a calibrator that dynamically suppresses sycophantic behavior when scores exceed predefined thresholds. Extensive experiments across 12 datasets and 3 LRMs demonstrate that our method effectively reduces sycophantic behavior in both intermediate reasoning steps and final answers, yielding robust performance improvements.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 33 of its 49 references that are in the map. First posted on arXiv 9 Nov 2025.

Builds on

33 of 49 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Understanding Reasoning in Thinking Language Models via Steering Vectors22 Jun
  2. 2025Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute18 Jun
  3. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 30

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  9. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  10. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  11. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 716
  12. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 703
18 more
  1. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 345
  2. 2024Programming Refusal with Conditional Activation Steeringcited by 206
  3. 2023Simple synthetic data reduces sycophancy in large language modelscited by 187
  4. 2025Thought Anchors: Which LLM Reasoning Steps Matter?cited by 129
  5. 2025SycEval: Evaluating LLM Sycophancycited by 108
  6. 2025Measuring Sycophancy of Language Models in Multi-turn Dialoguescited by 104
  7. 2023Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experimentcited by 77
  8. 2024From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuningcited by 54
  9. 2024Designing a Dashboard for Transparency and Control of Conversational AIcited by 46
  10. 2025Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trustcited by 34
  11. 2025TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Modelscited by 33
  12. 2023Fool Your (Vision and) Language Model With Embarrassingly Simple Permutationscited by 25
  13. 2025Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoningcited by 21
  14. 2025Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QAcited by 18
  15. 2025Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Modelscited by 17
  16. 2024Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Modelcited by 15
  17. 2024Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoringcited by 11
  18. 2024Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Stepcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 11.

12 papers.

  1. 2026Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?cited by 8
  2. 2026Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probingcited by 6
  3. 2026Controlling Repetition in Protein Language Modelscited by 5
  4. 2026Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stabilitycited by 5
  5. 2025Towards Reasoning-Preserving Unlearning in Multimodal Large Language Modelscited by 4
  6. 2026Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluationcited by 4
  7. 2026Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Modelscited by 3
  8. 2026Distortion Instead of Hallucination: The Effect of Reasoning Under Strict Constraintscited by 1
  9. 2026Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Modelscited by 1
  10. 2026Looking Again: Measuring Sycophancy in the Reasoning Chains of Multimodal Models Under Pressurecited by 1
  11. 2026SFAD: Speculative Factuality-Aware Decodingcited by 0
  12. 2026Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornnesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models
  2. 2025Thought calibration: Efficient and confident test-time scaling
  3. 2025Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
  4. 2026RAudit: A Blind Auditing Protocol for Large Language Model Reasoning
  5. 2026Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models
  6. 2026OBC-Prune: Outcome-Based Calibration for Large Reasoning Model Pruning
  7. 2025Reasoning Models Better Express Their Confidence
  8. 2026Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment