Overthinking in Language Models

Overview

This field studies why language models sometimes keep reasoning after reaching a useful answer, repeating steps, exploring unproductive branches, or even replacing a correct answer with a wrong one. Such behavior wastes tokens and latency in tasks like math, coding, and science question answering, and can also make agent behavior vulnerable to prompts or tool calls that trigger loops. Approaches include early stopping based on confidence, answer stability, or reasoning progress; difficulty-aware compute budgets; and training or inference-time methods that prune redundant steps or steer the model out of loops. The central tension is that useful deliberation and self-correction can look like waste, so reducing length must not sacrifice accuracy, faithfulness, or the ability to handle hard problems.

Latest papers

CardsList

74 papers6 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

  1. Adaptive Entropy-Sparing for Efficient Reasoning

    Nov 9, 2026Cong Jiang, Xiaofeng Zhang, Tom Ko +1Efficient Language Model ReasoningOverthinking in Language Models

  2. How Does Chain-of-Thought Supervision Teach Models to Reason? A Theoretical Analysis

    Nov 1, 2026Kaito Takanami, Cengiz Pehlevanerror propagation in large language model inferenceCoT Supervision

  3. Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation

    Oct 30, 2026Chanseul Cho, Jaesung Jun, Dongheon Lee +1Adaptive Reasoning in Language ModelsMLLM Reasoning

  4. CALM: Consistency-Aware Logit Masking in Decoding Space for Mitigating Overthinking of Large Reasoning Models

    Oct 19, 2026Shengjing Liu, Feiyang Li, Yuxuan Yang +2Overthinking in Language ModelsEfficient Language Model Reasoning

  5. Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers

    Oct 14, 2026Peilong Zhou, Hongtao Zhang, Yulong Huang +3Recurrent TransformersNeural Algorithmic Reasoning

  6. Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models

    Oct 9, 2026Weixin Guan, Liang Li, Shiyu Xie +7Overthinking in Language ModelsLLM Reasoning

  7. Settle: Learning When to Stop Reasoning

    Sep 30, 2026Ryan Brown, Zihao Fu, Chris RussellEarly Stopping for Language Model ReasoningEfficient Language Model Reasoning

  8. When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning

    Sep 30, 2026Yuanhe Zhang, Ziwei Wang, Jie Ren +6Language Model SteeringOverthinking in Language Models

  9. LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents

    Sep 25, 2026Dongsheng Xiao, Zeyuan Wang, Xuzhe Xia +2Overthinking in Language ModelsLLM Agents

  10. When2Think: Learning When and How Much to Reason

    Sep 17, 2026Jaejun Shim, HyunJin Kim, Young Jin Kim +1adaptive reasoning resource allocation for language modelsOverthinking in Language Models

  11. SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning

    Sep 15, 2026Qinhong Lin, Yuhao Zhang, Yinglun Feng +2Efficient Language Model ReasoningLLM Reasoning

  12. Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AI

    Aug 26, 2026Md Jueal Mia, M. Hadi AminiAgentic ReasoningOverthinking in Language Models

  13. Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning

    Aug 5, 2026Qiyuan Zhu, Dezhi Li, Pengyu Cheng +8Overthinking in Language ModelsKV Caching

  14. Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces

    Aug 4, 2026Francesca Carlon, Vincent Ginis, Andres AlgabaLLM EvaluationOverthinking in Language Models

  15. Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

    Jul 31, 2026Xinyan Guan, Jiali Zeng, Chunlei Xin +5Overthinking in Language ModelsRL for Language Model Reasoning

  16. QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization

    Jul 23, 2026Siwei Chen, Siqi Chen, Xupeng Miao +1Overthinking in Language ModelsRL for Language Model Reasoning

  17. Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

    Jul 20, 2026Sheldon Yu, Tong Yu, Xunyi Jiang +6Overthinking in Language ModelsCausal Interventions in Language Models

  18. UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention

    Jul 19, 2026Cheng Yan, Zhijun Fan, Guangyang Ye +4Adaptive InferenceOverthinking in Language Models

  19. Valid ≠\ne Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

    Jul 13, 2026Daeyeop Lee, Hwanjo YuLLM Inference EfficiencyOverthinking in Language Models

  20. OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping

    Jul 13, 2026Mohammed Ehab, Aymane El Gadarri, Vivek F. Farias +2Efficient Language Model ReasoningSequential Decision Making