Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their accuracy, but as the length of reasoning is further extended, it has also been shown to result in accuracy degradation and model instability. This work presents a novel sequential test-time scaling method, Min-Seek, which improves model accuracy significantly over a wide range of induced thoughts, stabilizing the accuracy of sequential scaling, and removing the need for reasoning length fine-tuning. Beyond improving model accuracy over a variety of reasoning tasks, our method is inherently efficient, as only the KV pairs of one additional induced thought are kept in the KV cache during reasoning. With a custom KV cache which stores keys without position embeddings, by dynamically encoding them contiguously before each new generated thought, our method can continue to reason well beyond a model's maximum context length, and under mild conditions has linear computational complexity.
When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学，中国）；University of California, Merced, USA（加州大学梅德福分校）；National Institute of Healthcare Data Science, Nanjing University, China（健康医疗数据科学国立研究所，南京大学，中国）
Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model
Zhejiang University（浙江大学）；Boston University（波士顿大学）；ByteDance（字节跳动）；School of Engineering, Westlake University（西溪大学工程学院）；Research Center for Industries of the Future, Westlake University（西溪大学未来产业研究中心）
Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University College London, University of London（伦敦大学大学学院）；Dalian University of Technology（大连理工大学）
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China（中国人民大学人工智能学院）；Beijing Key Laboratory of Research on Large Models（北京大型模型研究关键实验室）；Engineering Research Center of Next-Generation Intelligent Search（下一代智能搜索工程研究中心）；College of Artificial Intelligence, Tianjin University of Science（天津科技大学人工智能学院）
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
University of California, Santa Barbara（加州大学圣芭芭拉分校）；University of California, Santa Cruz（加州大学圣克ruz分校）；University of California, Los Angeles（加州大学洛杉矶分校）；Purdue University（普渡大学）；LMSYS Org（LMSYS组织）；Microsoft（微软）
Exploring the System 1 Thinking Capability of Large Reasoning Models
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Tongyi Lab, Alibaba Group（阿里巴巴集团通义实验室）
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）；Ant Group（蚂蚁集团）
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China（电子科技大学智能协同计算实验室）；Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province（四川省泛在智能与可信服务重点实验室）
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
Korea University（高丽大学）；dot（42dot）；Konkuk University（建国大学）；Yonsei University（延世大学）；Soongsil University（崇实大学）；Kumoh National Institute of Technology（金乌国立技术学院）
Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally
The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Peking University（北京大学）
The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
University of Science and Technology of China（中国科学技术大学）；SenseTime Research（商汤科技研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
