Large Reasoning Models

Follow this topic Ask about this topic

Large reasoning models study how language models can solve difficult problems by allocating computation across intermediate steps, tools, and alternative solution paths. Common approaches include reinforcement learning with verifiable rewards, supervised reasoning-trace distillation, tool use, search over sequential or parallel paths, and latent recurrent computation. Evaluation spans mathematics, coding, science question answering, logic, and multimodal tasks, measuring not only accuracy but also compute use, robustness, and the quality of intermediate reasoning. A central tension is that extra thinking can help on hard problems but also produce loops, errors, and safety risks, so researchers are developing adaptive stopping and compression while testing whether reasoning traces reliably reflect how answers are formed.

Latest papers

339 papers25 papers in the last four weeks, up 4% on the four weeks before. 0.1% of all new papers.

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
Aug 6, 2025Rui Ha, Rui Pu, Chaozhuo Li +2RL for Language Model Reasoning LLM Inference Acceleration
Beijing University of Posts and Telecommunications, China · 2Chongqing University of Posts and Telecommunications, China
Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
Aug 4, 2025Taihang Zhen, Jialiang Hong, Kai Chen +12RL for Language Model Reasoning CoT Compression
School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China · China Mobile (Suzhou) Software Technology Co., Ltd., Suzhou 215000, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China +2
HauntAttack: When Attack Follows Reasoning as a Shadow
Jun 8, 2025Jingyuan Ma, Rui Li, Zheng Li +4Adversarial Attacks on LLMs Jailbreak Attacks
State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University · StepFun · Department of Computing, The Hong Kong Polytechnic University +1
AI Mathematician: Towards Fully Automated Frontier Mathematical Research
May 28, 2025Yuanhang Liu, Yanxing Huang, Yanqiao Wang +2AI-Assisted Mathematical Discovery AI-Assisted Scientific Research
Qiuzhen College, Tsinghua University · Department of Mathematical Sciences, Tsinghua University · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China +1
ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
May 22, 2025Changyi Li, Jiayi Wang, Xudong Pan +2Language Model Safety Evaluation LLM Safety Benchmarks
Fudan University · Shanghai Innovation Institute
When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
May 21, 2025Rongzhi Zhu, Yi Liu, Jiancheng Wang +6Overthinking in Language Models LLM Interpretability
State Key Laboratory for Novel Software Technology, Nanjing University, China · China Unicom Software Research Institute, China · National Institute of Healthcare Data Science, Nanjing University, China +1
Scaling Evaluation-time Compute with Reasoning Models as Evaluators
Mar 25, 2025Seungone Kim, Ian Wu, Jinu Lee +8LLM Evaluation Language Model Generation Evaluation
CMU · UIUC2 · KAIST AI3 +3
The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
Feb 21, 2025Marthe Ballon, Andres Algaba, Vincent GinisCoT Reasoning Efficient Language Model Reasoning
Data Analytics Lab, Vrije Universiteit Brussel, Brussel 1050, Belgium · School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
Sep 27, 2024Tianyang Zhong, Zhengliang Liu, Yi Pan +74LLM Evaluation Code Generation

Aug 6, 2025J/K move · Enter open · S save

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control

Rui Ha, Rui Pu, Chaozhuo Li, Li Sun+1

Beijing University of Posts and Telecommunications, China · 2Chongqing University of Posts and Telecommunications, China

RL for Language Model Reasoning LLM Inference Acceleration LLM Reasoning Large Reasoning Models

Open paper AskPDF arXiv

Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking. As a result, LRMs continue generating redundant reasoning even after reaching high-confidence conclusions. This increases inference cost and latency, limiting practical deployment. The root cause is the absence of an intrinsic mechanism to monitor the reasoning state and decide when to continue, backtrack, or stop. We propose MERA, a meta-cognitive reasoning framework that decouples reasoning from control to enable independent optimization of control strategies. MERA constructs high-quality reasoning-control supervision data via a takeover-based pipeline, and transforms long-horizon traces into structured reasoning-control alternating sequences for training. The model is trained with supervised fine-tuning to internalize the structured separation, and further optimized with Control-Segment Policy Optimization (CSPO), which combines segment-wise GRPO with control masking to focus learning on control segments. Experiments across reasoning benchmarks show that MERA improves both efficiency and accuracy.