{"topic":{"slug":"reasoning-models","name":"Reasoning Models & Test-Time Compute","domain":"ai","description":"Chain-of-thought, reinforcement learning with verifiable rewards, process reward models and test-time scaling behind modern reasoning models.","keywords":["test-time compute","chain-of-thought","reasoning model","verifiable rewards","process reward model","test-time scaling","reinforcement learning reasoning"],"paper_count":233,"latest_published":"2026-10-27","url":"https://space-kitty.com/topics/reasoning-models","api_url":"https://space-kitty.com/api/v1/topics/reasoning-models"},"dossier":null,"top_papers":[{"id":"arxiv:2501.12948","kind":"article","title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning","authors":["Daya Guo","Dejian Yang","Haowei Zhang","Junxiao Song","Peiyi Wang","Qihao Zhu"],"author_count":100,"year":2025,"published":"2025-09-17","venue":"Nature","cited_by":1687,"doi":"10.1038/s41586-025-09422-z","arxiv_id":"2501.12948","nct_id":null,"source_url":"https://doi.org/10.1038/s41586-025-09422-z","archive_url":"https://space-kitty.com/papers/arxiv:2501.12948"},{"id":"arxiv:2201.11903","kind":"preprint","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","authors":["Wei, Jason","Wang, Xuezhi","Dale Schuurmans","Maarten Bosma","Brian Ichter","Fei Xia"],"author_count":9,"year":2022,"published":"2022-01-28","venue":null,"cited_by":4209,"doi":null,"arxiv_id":"2201.11903","nct_id":null,"source_url":"http://arxiv.org/abs/2201.11903","archive_url":"https://space-kitty.com/papers/arxiv:2201.11903"},{"id":"arxiv:2203.11171","kind":"preprint","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","authors":["Xuezhi Wang","Wei, Jason","Dale Schuurmans","Quoc Viet Le","Ed H.","Narang, Sharan"],"author_count":8,"year":2022,"published":"2022-03-21","venue":null,"cited_by":809,"doi":null,"arxiv_id":"2203.11171","nct_id":null,"source_url":"http://arxiv.org/abs/2203.11171","archive_url":"https://space-kitty.com/papers/arxiv:2203.11171"},{"id":"arxiv:2210.03629","kind":"preprint","title":"ReAct: Synergizing Reasoning and Acting in Language Models","authors":["Yao, Shunyu","Jeffrey W. Zhao","Dian Yu","Nan Du","Izhak Shafran J","Karthik Narasimhan"],"author_count":7,"year":2022,"published":"2022-10-06","venue":null,"cited_by":607,"doi":null,"arxiv_id":"2210.03629","nct_id":null,"source_url":"http://arxiv.org/abs/2210.03629","archive_url":"https://space-kitty.com/papers/arxiv:2210.03629"},{"id":"arxiv:2207.08143","kind":"article","title":"Can large language models reason about medical questions?","authors":["Valentin Liévin","Christoffer Hother","Andreas Geert Motzfeldt","Ole Winther"],"author_count":4,"year":2024,"published":"2024-03-01","venue":"Patterns","cited_by":343,"doi":"10.1016/j.patter.2024.100943","arxiv_id":"2207.08143","nct_id":null,"source_url":"https://doi.org/10.1016/j.patter.2024.100943","archive_url":"https://space-kitty.com/papers/arxiv:2207.08143"},{"id":"arxiv:2205.10625","kind":"preprint","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","authors":["Denny Zhou","Nathanael Schärli A","Le Hou","Wei, Jason","Scales, Nathan","Xuezhi Wang"],"author_count":11,"year":2022,"published":"2022-05-21","venue":null,"cited_by":379,"doi":null,"arxiv_id":"2205.10625","nct_id":null,"source_url":"http://arxiv.org/abs/2205.10625","archive_url":"https://space-kitty.com/papers/arxiv:2205.10625"},{"id":"doi:10.3390/healthcare11202776","kind":"review","title":"Leveraging Generative AI and Large Language Models: A Comprehensive Roadmap for Healthcare Integration","authors":["Ping Yu","Hua Xu","Xia Hu","Chao Deng"],"author_count":4,"year":2023,"published":"2023-10-20","venue":"Healthcare","cited_by":261,"doi":"10.3390/healthcare11202776","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3390/healthcare11202776","archive_url":"https://space-kitty.com/papers/doi:10.3390/healthcare11202776"},{"id":"arxiv:2312.03748","kind":"article","title":"Applying large language models and chain-of-thought for automatic scoring","authors":["Gyeong-Geon Lee","Ehsan Latif","Xuansheng Wu","Ninghao Liu","Xiaoming Zhaı"],"author_count":5,"year":2024,"published":"2024-02-27","venue":"Computers and Education Artificial Intelligence","cited_by":186,"doi":"10.1016/j.caeai.2024.100213","arxiv_id":"2312.03748","nct_id":null,"source_url":"https://doi.org/10.1016/j.caeai.2024.100213","archive_url":"https://space-kitty.com/papers/arxiv:2312.03748"},{"id":"arxiv:2210.03493","kind":"preprint","title":"Automatic Chain of Thought Prompting in Large Language Models","authors":["Zhuosheng Zhang","Aston Zhang","Mu Li","Alex J. Smola"],"author_count":4,"year":2022,"published":"2022-10-07","venue":null,"cited_by":274,"doi":null,"arxiv_id":"2210.03493","nct_id":null,"source_url":"http://arxiv.org/abs/2210.03493","archive_url":"https://space-kitty.com/papers/arxiv:2210.03493"},{"id":"doi:10.3390/medicina60030445","kind":"review","title":"Integrating Retrieval-Augmented Generation with Large Language Models in Nephrology: Advancing Practical Applications","authors":["Jing Miao","Charat Thongprayoon","Supawadee Suppadungsuk","Oscar A. Garcia Valencia","Wisit Cheungpasitporn"],"author_count":5,"year":2024,"published":"2024-03-08","venue":"Medicina","cited_by":168,"doi":"10.3390/medicina60030445","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3390/medicina60030445","archive_url":"https://space-kitty.com/papers/doi:10.3390/medicina60030445"},{"id":"doi:10.1145/3690635","kind":"article","title":"Structured Chain-of-Thought Prompting for Code Generation","authors":["Jia Li","Ge Li","Yongmin Li","Zhi Gang Jin"],"author_count":4,"year":2024,"published":"2024-08-29","venue":"ACM Transactions on Software Engineering and Methodology","cited_by":150,"doi":"10.1145/3690635","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1145/3690635","archive_url":"https://space-kitty.com/papers/doi:10.1145/3690635"},{"id":"arxiv:2310.08034","kind":"article","title":"Receive, Reason, and React: Drive as You Say, With Large Language Models in Autonomous Vehicles","authors":["Can Cui","Yunsheng Ma","Xu Cao","Wenqian Ye","Ziran Wang"],"author_count":5,"year":2024,"published":"2024-04-09","venue":"IEEE Intelligent Transportation Systems Magazine","cited_by":116,"doi":"10.1109/mits.2024.3381793","arxiv_id":"2310.08034","nct_id":null,"source_url":"https://doi.org/10.1109/mits.2024.3381793","archive_url":"https://space-kitty.com/papers/arxiv:2310.08034"},{"id":"arxiv:2211.10435","kind":"preprint","title":"PAL: Program-aided Language Models","authors":["Luyu Gao","Aman Madaan","Shuyan Zhou","Uri Alon","Pengfei Liu","Yiming Yang"],"author_count":8,"year":2022,"published":"2022-11-18","venue":null,"cited_by":155,"doi":null,"arxiv_id":"2211.10435","nct_id":null,"source_url":"http://arxiv.org/abs/2211.10435","archive_url":"https://space-kitty.com/papers/arxiv:2211.10435"},{"id":"doi:10.3390/medicina60010148","kind":"review","title":"Chain of Thought Utilization in Large Language Models and Application in Nephrology","authors":["Jing Miao","Charat Thongprayoon","Supawadee Suppadungsuk","Pajaree Krisanapan","Yeshwanter Radhakrishnan","Wisit Cheungpasitporn"],"author_count":6,"year":2024,"published":"2024-01-13","venue":"Medicina","cited_by":102,"doi":"10.3390/medicina60010148","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3390/medicina60010148","archive_url":"https://space-kitty.com/papers/doi:10.3390/medicina60010148"},{"id":"arxiv:2211.12588","kind":"preprint","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","authors":["Wenhu Chen","Xueguang Ma","Xinyi Wang","William W. Cohen"],"author_count":4,"year":2022,"published":"2022-11-22","venue":null,"cited_by":125,"doi":null,"arxiv_id":"2211.12588","nct_id":null,"source_url":"http://arxiv.org/abs/2211.12588","archive_url":"https://space-kitty.com/papers/arxiv:2211.12588"}],"newest_papers":[{"id":"arxiv:2610.36445","kind":"preprint","title":"From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation","authors":["Yashuo Luo","Qianren Mao","Ziqi Qin","Junnan Liu","Haitao Li","Qili Zhang"],"author_count":9,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36445","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36445","archive_url":"https://space-kitty.com/papers/arxiv:2610.36445"},{"id":"arxiv:2610.36709","kind":"preprint","title":"Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces","authors":["Pragna Mallappa"],"author_count":1,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36709","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36709","archive_url":"https://space-kitty.com/papers/arxiv:2610.36709"},{"id":"arxiv:2610.36849","kind":"preprint","title":"When All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning","authors":["Zehao Wang","Hanzhu Chen","Runquan Gui","Zhe Wang","Lin Yang"],"author_count":5,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36849","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36849","archive_url":"https://space-kitty.com/papers/arxiv:2610.36849"},{"id":"arxiv:2610.37041","kind":"preprint","title":"Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards","authors":["Bo Yang","Zishuai Zhang","Weihua Li","Qinnan Zhang","Sijia Wen","Hainan Zhang"],"author_count":6,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37041","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37041","archive_url":"https://space-kitty.com/papers/arxiv:2610.37041"},{"id":"arxiv:2610.37070","kind":"preprint","title":"Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluation","authors":["Yueer Pan","Yuexi Pan"],"author_count":2,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37070","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37070","archive_url":"https://space-kitty.com/papers/arxiv:2610.37070"},{"id":"arxiv:2610.37175","kind":"preprint","title":"MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model","authors":["Brian Ko","Han Wang","Hejia Geng","Li Erran Li","Sherry Yang"],"author_count":5,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37175","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37175","archive_url":"https://space-kitty.com/papers/arxiv:2610.37175"},{"id":"arxiv:2610.37211","kind":"preprint","title":"Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse","authors":["Jiafeng Liang","Xianhao Ou","Tao Ren","Rongchuan Mu","Runxuan Liu","Dandan Tu"],"author_count":9,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37211","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37211","archive_url":"https://space-kitty.com/papers/arxiv:2610.37211"},{"id":"arxiv:2610.37215","kind":"preprint","title":"Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution","authors":["Pham Tri Quang","Bao-Ngoc Dao","Minh Duc Nguyen","Duc-Duy Nguyen","Hung T. Ho","Linh Dang Le"],"author_count":18,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37215","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37215","archive_url":"https://space-kitty.com/papers/arxiv:2610.37215"},{"id":"arxiv:2610.37381","kind":"preprint","title":"PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations","authors":["Hanqing Wang","Zhaotian Cai","Ruichuan An","Bohan Zeng","Tao Zhang","Yilin Chen"],"author_count":15,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37381","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37381","archive_url":"https://space-kitty.com/papers/arxiv:2610.37381"},{"id":"arxiv:2610.37471","kind":"preprint","title":"PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions","authors":["Tongkun Guan","Zhibo Yang","Mingkun Yang","Haocheng Wang","Wei Shen","Xiaokang Yang"],"author_count":6,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.37471","nct_id":null,"source_url":"https://arxiv.org/abs/2610.37471","archive_url":"https://space-kitty.com/papers/arxiv:2610.37471"}],"related_topics":[{"slug":"llm-architectures","name":"LLM Architectures & Pretraining","api_url":"https://space-kitty.com/api/v1/topics/llm-architectures"},{"slug":"scaling-laws","name":"Scaling Laws & Compute-Optimal Training","api_url":"https://space-kitty.com/api/v1/topics/scaling-laws"},{"slug":"alignment-safety","name":"AI Alignment & Safety","api_url":"https://space-kitty.com/api/v1/topics/alignment-safety"},{"slug":"interpretability","name":"Mechanistic Interpretability","api_url":"https://space-kitty.com/api/v1/topics/interpretability"},{"slug":"ai-agents","name":"LLM Agents & Tool Use","api_url":"https://space-kitty.com/api/v1/topics/ai-agents"},{"slug":"generative-multimodal","name":"Generative & Multimodal Models","api_url":"https://space-kitty.com/api/v1/topics/generative-multimodal"},{"slug":"efficient-ai","name":"Efficient Training & Inference","api_url":"https://space-kitty.com/api/v1/topics/efficient-ai"},{"slug":"ai-for-science","name":"AI for Science","api_url":"https://space-kitty.com/api/v1/topics/ai-for-science"},{"slug":"robotics-embodied","name":"Robot Learning & Embodied AI","api_url":"https://space-kitty.com/api/v1/topics/robotics-embodied"}],"premium":{"dossier":null,"research_pack":{"url":"https://space-kitty.com/api/v1/topics/reasoning-models/pack","price_usd":"0.20"}},"more":"https://space-kitty.com/api/v1/topics/reasoning-models/papers?sort=top&limit=100"}