CoT Reasoning

CoT: Chain-of-Thought

Overview

Chain-of-thought reasoning studies how language models break complex problems into steps, use intermediate information, and produce answers that can be checked or acted on. Approaches include prompting models to show their work, training on reasoning traces with supervised learning or reinforcement learning, and using structured methods such as code, symbolic rules, trees, or latent reasoning states. Researchers test these methods on tasks including mathematics, multi-hop question answering, coding, clinical decisions, and visual or spatial understanding, while developing verification and adaptive-compute methods to control cost. A central tension is that longer or more detailed traces do not reliably improve accuracy or explain how a model reached its answer; they can also amplify errors, bias, or unsupported claims.

Latest papers

CardsList

244 papers18 papers in the last four weeks, down 25% on the four weeks before. 0.1% of all new papers.

  1. Chain-of-Thought Hidden States Reveal Task-Solving Directions for Direct Answers

    Nov 18, 2026Houman Mehrafarin, Ioannis KonstasCoT ReasoningEfficient Language Model Reasoning

  2. Pixel is All You Need

    Nov 17, 2026Jie Chu, Haoting Shi, Fucheng Zhang +4Generative ModelingUnified Multimodal Models

  3. RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation

    Nov 17, 2026Prashant Khatri, Bhavana Malagavalli, Saiful Haq +1CoT ReasoningStructured Reasoning in Language Models

  4. Towards Better Legal Reasoning LLMs: Signal Balancing and Reward Scheduling

    Nov 11, 2026Yinghao Hu, Qian Xiao, Yuting Huang +7Legal ReasoningStructured Reasoning in Language Models

  5. Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation

    Nov 10, 2026Jiawei Xiao, Boya Wang, Longtian Qiu +2Relational Representation LearningRepresentation Learning

  6. When Reasoning looks like Hidden Understanding: How Chain-of-Thought Fosters Anthropomorphism, Perceptions of Epistemic Superiority, and Cognitive Deference

    Nov 10, 2026Oliver Lack, Lana Tikhomirov, Humphrey Thompson +2Anthropomorphism in AICoT Reasoning

  7. RoadState: A Domain-Prior-Enhanced Vision-Language System for Industrial-Grade Lane-Level Map Updating

    Nov 7, 2026Deguo Xia, Zihan Li, Jiaqi Wang +11VLMs for Autonomous DrivingHD Map Construction

  8. A Tight Hierarchy for Chain of Thought

    Nov 6, 2026Thanh Le, A. Pavan, N. V. VinodchandranCoT ReasoningStructured Reasoning in Language Models

  9. BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning

    Nov 6, 2026Yiyu Gui, Mingzhi Chen, Guibo Luo +1EEG Foundation ModelsZero-Shot Learning

  10. Where and Why is Grounded Reasoning Useful?

    Nov 5, 2026David Yan, Le Xue, Forrest Huang +4Visually Grounded ReasoningVisual Reasoning

  11. Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs

    Nov 4, 2026Nuo-Jing Liang, Xiao-Tong Yuan, Pan ZhouCoT ReasoningOOD Generalization

  12. REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories

    Oct 23, 2026Hanwen Zhang, Enyi Jiang, Ruike Zhu +2LLM SafetyCausal Interventions in Language Models

  13. Transformers with CoT Discover Heavy-Ball Acceleration Through Training

    Oct 22, 2026Yuxuan Cai, Yuan CaoIn-Context RegressionCoT Reasoning

  14. Sparse RL Relaxation for LLM Reasoning

    Oct 19, 2026Jiabin Fan, Matthias Lindemann, Zita Marinho +2CoT ReasoningRL for Language Model Reasoning

  15. Internalizing Chain-of-thought into Looped Transformers

    Oct 19, 2026Kehang Zhou, Pinyan LuRecurrent TransformersLatent Reasoning

  16. Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation

    Oct 18, 2026Junwei Wen, Deshui Miao, Guangming Lu +3Temporal Reasoning in VLMsVideo Object Segmentation

  17. The Density of Thought: Predicting and Steering Reasoning in Large Language Models

    Oct 15, 2026Tanush Kalhan, Anupam Chattopadhyay, Sriram Ranga +1Language Model SteeringCoT Reasoning

  18. CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation

    Oct 14, 2026Zinan Tang, Zhuoshi Pan, Kairui Chen +5CoT DistillationLanguage Model Distillation

  19. Frustratingly Easy Majority Voting Using Length Conditioning

    Oct 14, 2026Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu +4LLM ReasoningEfficient Language Model Reasoning

  20. Integrating Simulation and Chain-of-thought Reasoning in Multimodal-Language Models For Physical Reasoning

    Oct 14, 2026YingQiao Wang, Eric Bigelow, Tomer Ullman +2Multimodal ReasoningCoT Reasoning

  21. The Surprising Expressivity of a Single Neuron with Autoregressive Chain-of-Thought

    Oct 12, 2026Roey Magen, Nirmit Joshi, Gal VardiNeural Network ExpressivityCoT Reasoning

  22. Reasoning for Propaganda Detection via Label-Guided CoT Optimisation

    Oct 12, 2026Zeba Afroz, Harsh Vardhan, Md. Shad AkhtarExplainable Text ClassificationPropaganda Detection

  23. One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought

    Oct 12, 2026Lyumin Wu, Yuan CaoTransformerIn-Context Learning

  24. Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training

    Oct 9, 2026Suorong Yang, Jiaxin Wang, Jiaming Su +4Efficient Language Model ReasoningEfficient Language Model Training