# Reasoning Models & Test-Time Compute Domain: Artificial Intelligence · 233 papers indexed · newest 2026-10-27 Chain-of-thought, reinforcement learning with verifiable rewards, process reward models and test-time scaling behind modern reasoning models. Key concepts: test-time compute, chain-of-thought, reasoning model, verifiable rewards, process reward model, test-time scaling, reinforcement learning reasoning ## Most influential - **[DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning](https://space-kitty.com/papers/arxiv:2501.12948)**. Daya Guo, Dejian Yang, Haowei Zhang et al. · 2025 · Nature (arXiv:2501.12948 · doi:10.1038/s41586-025-09422-z · 1,687 citations). Source: > General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labeled reasoning trajectorie… - **[Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://space-kitty.com/papers/arxiv:2201.11903)**. Wei, Jason, Wang, Xuezhi, Dale Schuurmans et al. · 2022 (arXiv:2201.11903 · 4,209 citations). Source: > We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. Th… - **[Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://space-kitty.com/papers/arxiv:2203.11171)**. Xuezhi Wang, Wei, Jason, Dale Schuurmans et al. · 2022 (arXiv:2203.11171 · 809 citations). Source: > Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out the sampled reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to i… - **[ReAct: Synergizing Reasoning and Acting in Language Models](https://space-kitty.com/papers/arxiv:2210.03629)**. Yao, Shunyu, Jeffrey W. Zhao, Dian Yu et al. · 2022 (arXiv:2210.03629 · 607 citations). Source: > While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it … - **[Can large language models reason about medical questions?](https://space-kitty.com/papers/arxiv:2207.08143)**. Valentin Liévin, Christoffer Hother, Andreas Geert Motzfeldt et al. · 2024 · Patterns (arXiv:2207.08143 · doi:10.1016/j.patter.2024.100943 · 343 citations). Source: > Although large language models (LLMs) often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge. We set out to investigate whether close- and open-source models (GPT-3.5, LLama-2, etc.) can be applied to answer and reason about difficult real-world-based questions. We focus on three popular medical benchmarks (MedQA-USMLE, MedMCQA, and PubMedQA) and multiple prompting scenarios: Chain-of-Thought (CoT, think step-by-step), few-shot and retrieval augmentation. Based on an expert annotation of the ge… - **[Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://space-kitty.com/papers/arxiv:2205.10625)**. Denny Zhou, Nathanael Schärli A, Le Hou et al. · 2022 (arXiv:2205.10625 · 379 citations). Source: > Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on tasks which requires solving problems harder than the exemplars shown in the prompts. To overcome this challenge of easy-to-hard generalization, we propose a novel prompting strategy, least-to-most prompting. The key idea in this strategy is to break down a complex problem into a series of simpler subproblems and then solve them in sequence. Solving each subproblem is facilitated by the answers to previously solved subproblems. Our experimental … - **[Leveraging Generative AI and Large Language Models: A Comprehensive Roadmap for Healthcare Integration](https://space-kitty.com/papers/doi:10.3390/healthcare11202776)**. Ping Yu, Hua Xu, Xia Hu et al. · 2023 · Healthcare (doi:10.3390/healthcare11202776 · 261 citations). Source: > Generative artificial intelligence (AI) and large language models (LLMs), exemplified by ChatGPT, are promising for revolutionizing data and information management in healthcare and medicine. However, there is scant literature guiding their integration for non-AI professionals. This study conducts a scoping literature review to address the critical need for guidance on integrating generative AI and LLMs into healthcare and medical practices. It elucidates the distinct mechanisms underpinning these technologies, such as Reinforcement Learning from Human Feedback (RLFH), including few-shot learn… > _Abstract excerpt by Ping Yu et al., CC-BY, https://doi.org/10.3390/healthcare11202776; truncated._ - **[Applying large language models and chain-of-thought for automatic scoring](https://space-kitty.com/papers/arxiv:2312.03748)**. Gyeong-Geon Lee, Ehsan Latif, Xuansheng Wu et al. · 2024 · Computers and Education Artificial Intelligence (arXiv:2312.03748 · doi:10.1016/j.caeai.2024.100213 · 186 citations). Source: > This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the challenges of accessibility, technical complexity, and lack of explainability that have previously limited the use of artificial intelligence-based automatic scoring tools among researchers and educators. With a testing dataset comprising six assessment tasks (three binomial and three trinomial) with 1,650 student responses, we employed six prompt engineering… - **[Automatic Chain of Thought Prompting in Large Language Models](https://space-kitty.com/papers/arxiv:2210.03493)**. Zhuosheng Zhang, Aston Zhang, Mu Li et al. · 2022 (arXiv:2210.03493 · 274 citations). Source: > Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One leverages a simple prompt like "Let's think step by step" to facilitate step-by-step thinking before answering a question. The other uses a few manual demonstrations one by one, each composed of a question and a reasoning chain that leads to an answer. The superior performance of the second paradigm hinges on the hand-crafting of task-specific demonstration… - **[Integrating Retrieval-Augmented Generation with Large Language Models in Nephrology: Advancing Practical Applications](https://space-kitty.com/papers/doi:10.3390/medicina60030445)**. Jing Miao, Charat Thongprayoon, Supawadee Suppadungsuk et al. · 2024 · Medicina (doi:10.3390/medicina60030445 · 168 citations). Source: > The integration of large language models (LLMs) into healthcare, particularly in nephrology, represents a significant advancement in applying advanced technology to patient care, medical research, and education. These advanced models have progressed from simple text processors to tools capable of deep language understanding, offering innovative ways to handle health-related data, thus improving medical practice efficiency and effectiveness. A significant challenge in medical applications of LLMs is their imperfect accuracy and/or tendency to produce hallucinations-outputs that are factually in… > _Abstract excerpt by Jing Miao et al., CC-BY, https://doi.org/10.3390/medicina60030445; truncated._ - **[Structured Chain-of-Thought Prompting for Code Generation](https://space-kitty.com/papers/doi:10.1145/3690635)**. Jia Li, Ge Li, Yongmin Li et al. · 2024 · ACM Transactions on Software Engineering and Methodology (doi:10.1145/3690635 · 150 citations). Source: - **[Receive, Reason, and React: Drive as You Say, With Large Language Models in Autonomous Vehicles](https://space-kitty.com/papers/arxiv:2310.08034)**. Can Cui, Yunsheng Ma, Xu Cao et al. · 2024 · IEEE Intelligent Transportation Systems Magazine (arXiv:2310.08034 · doi:10.1109/mits.2024.3381793 · 116 citations). Source: > The fusion of human-centric design and artificial intelligence (AI) capabilities has opened up new possibilities for next-generation autonomous vehicles that go beyond transportation. These vehicles can dynamically interact with passengers and adapt to their preferences. This paper proposes a novel framework that leverages Large Language Models (LLMs) to enhance the decision-making process in autonomous vehicles. By utilizing LLMs' linguistic and contextual understanding abilities with specialized tools, we aim to integrate the language and reasoning capabilities of LLMs into autonomous vehicl… - **[PAL: Program-aided Language Models](https://space-kitty.com/papers/arxiv:2211.10435)**. Luyu Gao, Aman Madaan, Shuyan Zhou et al. · 2022 (arXiv:2211.10435 · 155 citations). Source: > Large language models (LLMs) have recently demonstrated an impressive ability to perform arithmetic and symbolic reasoning tasks, when provided with a few examples at test time ("few-shot prompting"). Much of this success can be attributed to prompting methods such as "chain-of-thought'', which employ LLMs for both understanding the problem description by decomposing it into steps, as well as solving each step of the problem. While LLMs seem to be adept at this sort of step-by-step decomposition, LLMs often make logical and arithmetic mistakes in the solution part, even when the problem is dec… - **[Chain of Thought Utilization in Large Language Models and Application in Nephrology](https://space-kitty.com/papers/doi:10.3390/medicina60010148)**. Jing Miao, Charat Thongprayoon, Supawadee Suppadungsuk et al. · 2024 · Medicina (doi:10.3390/medicina60010148 · 102 citations). Source: > Chain-of-thought prompting enhances the abilities of large language models (LLMs) significantly. It not only makes these models more specific and context-aware but also impacts the wider field of artificial intelligence (AI). This approach broadens the usability of AI, increases its efficiency, and aligns it more closely with human thinking and decision-making processes. As we improve this method, it is set to become a key element in the future of AI, adding more purpose, precision, and ethical consideration to these technologies. In medicine, the chain-of-thought prompting is especially benef… > _Abstract excerpt by Jing Miao et al., CC-BY, https://doi.org/10.3390/medicina60010148; truncated._ - **[Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://space-kitty.com/papers/arxiv:2211.12588)**. Wenhu Chen, Xueguang Ma, Xinyi Wang et al. · 2022 (arXiv:2211.12588 · 125 citations). Source: > Recently, there has been significant progress in teaching language models to perform step-by-step reasoning to solve complex numerical reasoning tasks. Chain-of-thoughts prompting (CoT) is by far the state-of-art method for these tasks. CoT uses language models to perform both reasoning and computation in the multi-step \`thought' process. To disentangle computation from reasoning, we propose \`Program of Thoughts' (PoT), which uses language models (mainly Codex) to express the reasoning process as a program. The computation is relegated to an external computer, which executes the generated prog… ## Newest - **[From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation](https://space-kitty.com/papers/arxiv:2610.36445)**. Yashuo Luo, Qianren Mao, Ziqi Qin et al. · 2026 (arXiv:2610.36445). Source: - **[Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces](https://space-kitty.com/papers/arxiv:2610.36709)**. Pragna Mallappa · 2026 (arXiv:2610.36709). Source: - **[When All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning](https://space-kitty.com/papers/arxiv:2610.36849)**. Zehao Wang, Hanzhu Chen, Runquan Gui et al. · 2026 (arXiv:2610.36849). Source: - **[Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards](https://space-kitty.com/papers/arxiv:2610.37041)**. Bo Yang, Zishuai Zhang, Weihua Li et al. · 2026 (arXiv:2610.37041). Source: - **[Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluation](https://space-kitty.com/papers/arxiv:2610.37070)**. Yueer Pan, Yuexi Pan · 2026 (arXiv:2610.37070). Source: - **[MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model](https://space-kitty.com/papers/arxiv:2610.37175)**. Brian Ko, Han Wang, Hejia Geng et al. · 2026 (arXiv:2610.37175). Source: - **[Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse](https://space-kitty.com/papers/arxiv:2610.37211)**. Jiafeng Liang, Xianhao Ou, Tao Ren et al. · 2026 (arXiv:2610.37211). Source: - **[Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution](https://space-kitty.com/papers/arxiv:2610.37215)**. Pham Tri Quang, Bao-Ngoc Dao, Minh Duc Nguyen et al. · 2026 (arXiv:2610.37215). Source: - **[PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations](https://space-kitty.com/papers/arxiv:2610.37381)**. Hanqing Wang, Zhaotian Cai, Ruichuan An et al. · 2026 (arXiv:2610.37381). Source: - **[PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions](https://space-kitty.com/papers/arxiv:2610.37471)**. Tongkun Guan, Zhibo Yang, Mingkun Yang et al. · 2026 (arXiv:2610.37471). Source: --- Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.