English
Related papers

Related papers: Anti-Length Shift: Dynamic Outlier Truncation for …

200 papers

While recent success of large reasoning models (LRMs) significantly advanced LLMs' reasoning capability by optimizing the final answer accuracy using reinforcement learning, they may also drastically increase the output length due to…

Artificial Intelligence · Computer Science 2025-05-29 Sohyun An , Ruochen Wang , Tianyi Zhou , Cho-Jui Hsieh

Large Reasoning Language Models (LRLMs) demonstrate impressive capabilities on complex tasks by utilizing long Chain-of-Thought reasoning. However, they are prone to overthinking, which generates redundant reasoning steps that degrade both…

Computation and Language · Computer Science 2026-03-17 Weixin Guan , Liang Li , Jiapeng Liu , Bing Li , Peng Fu , Chengyang Fang , Xiaoshuai Hao , Can Ma , Weiping Wang

Chain-of-Thought (CoT) reasoning has driven recent gains of large language models (LLMs) on reasoning-intensive tasks by externalizing intermediate steps. However, excessive or redundant reasoning -- so-called overthinking -- can increase…

Computation and Language · Computer Science 2025-10-14 Renliang Sun , Wei Cheng , Dawei Li , Haifeng Chen , Wei Wang

Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, largely due to the…

Computation and Language · Computer Science 2026-01-19 Kun Li , Zenan Xu , Junan Li , Zengrui Jin , Jinghao Deng , Zexuan Qiu , Bo Zhou

With the rapid advancement of large reasoning models, long Chain-of-Thought (CoT) prompting has demonstrated strong performance on complex tasks. However, this often comes with a significant increase in token usage. In this paper, we…

Computation and Language · Computer Science 2025-06-05 Ruiqi Zhang , Changyi Xiao , Yixin Cao

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit…

Artificial Intelligence · Computer Science 2026-04-21 Benteng Chen , Weida Wang , Shufei Zhang , Mingbao Lin , Min Zhang

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens,…

Computation and Language · Computer Science 2025-06-11 Tergel Munkhbat , Namgyu Ho , Seo Hyun Kim , Yongjin Yang , Yujin Kim , Se-Young Yun

Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks, largely due to the adoption of Long Chain-of-Thought (Long CoT) reasoning. However, they often exhibit overthinking -- performing unnecessary…

Computation and Language · Computer Science 2025-05-30 Keqin Peng , Liang Ding , Yuanxin Ouyang , Meng Fang , Dacheng Tao

Large Language Models (LLMs) employ Chain-of-Thought (CoT) reasoning to deconstruct complex problems. While longer CoTs are often presumed superior, this paper challenges that notion, arguing that longer is not always better. Drawing on…

Artificial Intelligence · Computer Science 2025-05-28 Yuyang Wu , Yifei Wang , Ziyu Ye , Tianqi Du , Stefanie Jegelka , Yisen Wang

Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge distillation (KD) over lengthy sequences with prompt (P),…

Computation and Language · Computer Science 2026-01-09 Wei-Rui Chen , Vignesh Kothapalli , Ata Fatahibaarzi , Hejian Sang , Shao Tang , Qingquan Song , Zhipeng Wang , Muhammad Abdul-Mageed

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value…

Artificial Intelligence · Computer Science 2025-11-13 Michael Kleinman , Matthew Trager , Alessandro Achille , Wei Xia , Stefano Soatto

Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy…

Machine Learning · Computer Science 2026-04-20 Hanbing Liu , Lang Cao , Yuanyi Ren , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it indiscriminately…

Machine Learning · Computer Science 2025-05-27 Chenwei Lou , Zewei Sun , Xinnian Liang , Meng Qu , Wei Shen , Wenqi Wang , Yuntao Li , Qingping Yang , Shuangzhi Wu

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

Information Retrieval · Computer Science 2026-05-15 Danyang Liu , Kan Li

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

Machine Learning · Computer Science 2026-05-12 Songtao Wei , Yi Li , Zhikai Li , Xu Hu , Yuede Ji , Guanpeng Li , Feng Chen , Carl Yang , Zhichun Guo , Bingzhe Li

Large Reasoning Models (LRMs) often suffer from overthinking, generating verbose reasoning traces that compromise both computational efficiency and interpretability. Unlike prior efforts that rely on global length-based rewards, we propose…

Artificial Intelligence · Computer Science 2026-01-07 Jialiang Hong , Taihang Zhen , Kai Chen , Jiaheng Liu , Junlan Feng , Wenpeng Zhu , Jing Huo , Yang Gao , Depeng Wang , Haitao Wan , Xi Yang , Boyan Wang , Fanyu Meng , Yuyao Zhang

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Computation and Language · Computer Science 2025-09-30 Yijun Tian , Shaoyu Chen , Zhichao Xu , Yawei Wang , Jinhe Bi , Peng Han , Wei Wang

Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct solution has already been reached. Existing early reasoning exit methods primarily rely on…

Computation and Language · Computer Science 2026-04-17 Kang Liu , Yongkang Liu , Xiaocui Yang , Peidong Wang , Wen Zhang , Shi Feng , Yifei Zhang , Daling Wang

Complex Reasoning in Large Language Models can be dynamically optimized using Test-Time Scaling (TTS) to mitigate Overthinking. Methods such as Coconut, SoftCoT and its variant are effective in continuous latent space inference, the core…

Artificial Intelligence · Computer Science 2025-12-17 Jiaqi Wang , Binquan Ji , Haibo Luo , Yiyang Qi , Ruiting Li , Huiyan Wang , Yuantao Han , Cangyi Yang , jiaxu Zhang , Feiliang Ren

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Computation and Language · Computer Science 2025-08-11 Ruosen Li , Ziming Luo , Quan Zhang , Ruochen Li , Ben Zhou , Ali Payani , Xinya Du