English
Related papers

Related papers: Entropy After </Think> for reasoning model early e…

200 papers

Reasoning large language models achieve impressive test-time scaling by thinking for longer, but this performance gain comes at significant compute cost. Directly limiting test-time budget hurts overall performance, but not all problems are…

Machine Learning · Computer Science 2025-05-27 Menghua Wu , Cai Zhou , Stephen Bates , Tommi Jaakkola

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Computation and Language · Computer Science 2025-10-16 Yang Li , Zhichen Dong , Yuhan Sun , Weixun Wang , Shaopan Xiong , Yijia Luo , Jiashun Liu , Han Lu , Jiamang Wang , Wenbo Su , Bo Zheng , Junchi Yan

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths…

Artificial Intelligence · Computer Science 2026-04-03 Yulin Li , Tengyao Tu , Li Ding , Junjie Wang , Huiling Zhen , Yixin Chen , Yong Li , Zhuotao Tian

Since the inception of Large Language Models (LLMs), the quest to efficiently train them for superior reasoning capabilities has been a pivotal challenge. The dominant training paradigm for LLMs is based on next token prediction (NTP).…

Computation and Language · Computer Science 2025-02-21 Pengxiao Lin , Zhongwang Zhang , Zhi-Qin John Xu

Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and reasoning path collapse when grounded in discrete token spaces. Recent latent reasoning…

Artificial Intelligence · Computer Science 2026-02-05 Jiecong Wang , Hao Peng , Chunyang Liu

Recent advances in large reasoning models have enabled complex, step-by-step reasoning but often introduce significant overthinking, resulting in verbose and redundant outputs that hinder efficiency. In this study, we examine whether…

Computation and Language · Computer Science 2025-06-19 Chenlong Wang , Yuanning Feng , Dongping Chen , Zhaoyang Chu , Ranjay Krishna , Tianyi Zhou

Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce…

Artificial Intelligence · Computer Science 2025-12-04 Emil Biju , Shayan Talaei , Zhemin Huang , Mohammadreza Pourreza , Azalia Mirhoseini , Amin Saberi

Recently, large reasoning models have achieved impressive performance on various tasks by employing human-like deep thinking. However, the lengthy thinking process substantially increases inference overhead, making efficiency a critical…

Computation and Language · Computer Science 2025-05-20 Jiajie Zhang , Nianyi Lin , Lei Hou , Ling Feng , Juanzi 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

When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…

Computation and Language · Computer Science 2024-03-19 Eric Zelikman , Georges Harik , Yijia Shao , Varuna Jayasiri , Nick Haber , Noah D. Goodman

Recent thinking models trained with reinforcement learning and backward-checking CoT often suffer from overthinking: they produce excessively long outputs even on simple problems, wasting computation. Existing evaluations, based on token…

Computation and Language · Computer Science 2025-10-15 Siqi Fan , Bowen Qin , Peng Han , Shuo Shang , Yequan Wang , Aixin Sun

Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing methods often either increase response length indiscriminately or shorten responses at…

Computation and Language · Computer Science 2026-05-20 Shuyu Wei , Jian Sun , Delai Qiu , Yining Wang , Shengping Liu , Jiaen Liang , Ying Fu , Wei Huang , Jitao Sang

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Computation and Language · Computer Science 2026-01-01 Tiancheng Su , Meicong Zhang , Guoxiu He

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

Artificial Intelligence · Computer Science 2025-12-23 Qinglin Zeng , Jing Yang , Keze Wang

Large Language Models (LLMs) struggle with reliable mathematical reasoning, and current verification methods are often computationally expensive. This paper introduces the Energy Outcome Reward Model (EORM), a highly efficient, lightweight…

Chain-of-Thought (CoT) reasoning has demonstrated remarkable effectiveness in enhancing the reasoning abilities of large language models (LLMs). However, its efficiency remains a challenge due to the generation of excessive intermediate…

Artificial Intelligence · Computer Science 2025-08-20 Jianshu She , Zhuohao Li , Zhemin Huang , Qi Li , Peiran Xu , Haonan Li , Qirong Ho

Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted…

Artificial Intelligence · Computer Science 2026-02-10 Ziwei Wang , Yuanhe Zhang , Jing Chen , Zhenhong Zhou , Ruichao Liang , Ruiying Du , Ju Jia , Cong Wu , Yang Liu

Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions, which is essential for natural social interaction. Although recent progress in Large Reasoning Models (LRMs) has boosted…

Artificial Intelligence · Computer Science 2026-03-05 Nanxu Gong , Haotian Li , Sixun Dong , Jianxun Lian , Yanjie Fu , Xing Xie

Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. However, explicit CoT methods rely on discrete token-level…

Computation and Language · Computer Science 2025-11-11 Zhikang Chen , Sen Cui , Deheng Ye , Yu Zhang , Yatao Bian , Tingting Zhu

To enhance reasoning capabilities, previous works have explored incorporating special-purpose tokens into the training process. These strategies strengthen the learning mechanism of transformer-based large language models (LLMs). Building…

Computation and Language · Computer Science 2025-08-12 Eunki Kim , Sangryul Kim , James Thorne