v1v2 (latest)

LightThinker: Thinking Step-by-Step Compression

21 February 2025

ArXiv (abs)PDF HTML HuggingFace (29 upvotes)Github (101★)

Papers citing "LightThinker: Thinking Step-by-Step Compression"

41 / 41 papers shown

Title
Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models Yang Xiang Yixin Ji Juntao Li Min Zhang LRM 84 0 0 24 Nov 2025
Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement Jiashu Yao Heyan Huang Shuang Zeng Chuwei Luo Wangjie You Jie Tang Qingsong Liu Yuhang Guo Yangyang Kang ReLM KELM 252 0 0 20 Nov 2025
StreamingThinker: Large Language Models Can Think While Reading Junlong Tong Yingqi Fan Anhao Zhao Yunpu Ma Xiaoyu Shen RALM LRM 291 1 0 20 Oct 2025
Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think? Shouren Wang Wang Yang Xianxuan Long Qifan Wang Vipin Chaudhary Xiaotian Han LRM 236 0 0 14 Oct 2025
Mitigating Overthinking through Reasoning Shaping Feifan Song Shaohang Wei Bofei Gao Yejie Wang Wen Luo ... Linli Yao Weimin Xiong L. Chen Tianyu Liu Houfeng Wang LRM 92 0 0 10 Oct 2025
Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression Chengzhengxu Li Xiaoming Liu Zhaohan Zhang Shaochu Zhang Shengchao Liu Guoxin Ma Y. Lan Chao Shen LRM 108 0 0 09 Oct 2025
ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models Akshat Ramachandran Marina Neseem Charbel Sakr Rangharajan Venkatesan Brucek Khailany Tushar Krishna MQ LRM VLM 137 1 1 01 Oct 2025
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement Jianzhi Yan Le Liu Youcheng Pan Shiwei Chen Zike Yuan Yang Xiang Buzhou Tang MQ LRM 73 0 0 26 Sep 2025
MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning Yapeng Mi Hengli Li Yanpeng Zhao Chenxi Li Huimin Wu Xiaojian Ma Song-Chun Zhu Ying Nian Wu Qing Li LRM VLM 1.3K 2 0 26 Sep 2025
Implicit Reasoning in Large Language Models: A Comprehensive Survey Jindong Li Yali Fu Li Fan Jiahong Liu Yao Shu Chengwei Qin Menglin Yang Irwin King Rex Ying OffRL LRM AI4CE 176 10 0 02 Sep 2025
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models Qianyu He Siyu Yuan Xuefeng Li Mingxuan Wang Jiangjie Chen RALM LRM 78 2 0 26 Aug 2025
Meta-R1: Empowering Large Reasoning Models with Metacognition Haonan Dong Haoran Ye Wenhao Zhu Kehan Jiang Guojie Song ReLM LRM AI4CE 112 2 0 24 Aug 2025
A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures Dezhang Kong Shi Lin Zhenhua Xu Z. J. Wang Minghao Li ... Ningyu Zhang Chaochao Chen Chunming Wu Muhammad Khurram Khan Meng Han LLMAG 195 22 0 24 Jun 2025
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning Haoyue Zhang Hualei Zhang Xiaosong Ma Jie Zhang Song Guo LRM 233 1 0 19 Jun 2025
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents Zijian Zhou Ao Qu Zhaoxuan Wu Sunghwan Kim Alok Prakash Daniela Rus Jinhua Zhao Bryan Kian Hsiang Low Paul Liang LLMAG OffRL LRM 370 37 0 18 Jun 2025
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills Changsheng Wang Chongyu Fan Yihua Zhang Jinghan Jia Dennis Wei Parikshit Ram Nathalie Baracaldo Sijia Liu MU KELM LRM 299 7 0 15 Jun 2025
Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements Seyed Moein Abtahi Akramul Azim 268 4 0 12 Jun 2025
EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Jinghan Jia Hadi Reisizadeh Chongyu Fan Nathalie Baracaldo Mingyi Hong Sijia Liu LRM 278 0 0 04 Jun 2025
A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings Xiaoang Xu Kaiyan Zhang Xu Han Zhenghao Liu Huijia Wu P. Li Zhiyuan Liu Maosong Sun Zhaofeng He LRM 667 2 0 30 May 2025
Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting Yifan Wu Jingze Shi Yiran Peng Jiayi Zhang Xiaotian Lin Nan Tang Yuyu Luo LRM 232 7 0 26 May 2025
Efficient Long CoT Reasoning in Small Language Models Z. Wang Jinqi Jiang Tian Qiu Hui Liu Xianfeng Tang Huaxiu Yao OffRL ReLM LRM 241 3 0 24 May 2025
Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning Xinghao Chen Anhao Zhao Heming Xia Xuan Lu Hanlin Wang Yanjun Chen Wei Zhang Jian Wang W. Li Xiaoyu Shen ReLM LRM 357 15 0 22 May 2025
ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy Gengyang Li Yifeng Gao Yuming Li Yunfang Wu ReLM OffRL LRM 376 13 0 21 May 2025
FlashThink: An Early Exit Method For Efficient Reasoning Guochao Jiang Guofeng Quan Zepeng Ding Ziqin Luo Dixuan Wang Zheng Hu ReLM LRM 185 13 0 20 May 2025
Let LRMs Break Free from Overthinking via Self-Braking Tuning Haoran Zhao Yuchen Yan Yongliang Shen Haolei Xu Wenqi Zhang Kaitao Song Jian Shao Weiming Lu Jun Xiao Yueting Zhuang LRM 353 12 0 20 May 2025
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs Zheyu Shen Ziyao Wang Bowei Tian Meng Liu Sihan Chen Shwai He Bowei Tian Wanghao Ye Yiting Wang Ang Li LRM 214 3 0 19 May 2025
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning Yang Liu Ming Ma Xiaomin Yu Pengxiang Ding Han Zhao Mingyang Sun Siteng Huang Xuetao Zhang LRM 462 19 0 18 May 2025
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning Ziqing Qiao Yongheng Deng Jiali Zeng Dong Wang Lai Wei Fandong Meng Jie Zhou Jie Zhou Ju Ren Yaoxue Zhang LRM 393 19 0 08 May 2025
Efficient Reasoning for LLMs through Speculative Chain-of-Thought Jikai Wang Junlin Li Jianye Hou Hao Fei Lijun Wu Min Zhang LLMAG LRM 316 11 0 27 Apr 2025
Efficient Reasoning Models: A Survey Sicheng Feng Gongfan Fang Xinyin Ma Xinchao Wang ReLM LRM 858 40 0 15 Apr 2025
S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models Wenyuan Zhang Jiawei Sheng Xinghua Zhang Zefeng Zhang Tingwen Liu ELM LRM 427 12 0 14 Apr 2025
Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time Wang Yang Xiang Yue Vipin Chaudhary Xiaotian Han ReLM LRM 272 26 0 12 Apr 2025
Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning Ximing Lu Seungju Han David Acuna Hyunwoo Kim Jaehun Jung ... Niklas Muennighoff M. Patwary Mohammad Shoeybi Bryan Catanzaro Yejin Choi ReLM LRM 296 14 0 06 Apr 2025
Efficient Inference for Large Reasoning Models: A Survey Yi Liu Jiaying Wu Yufei He Hongcheng Gao Hongyu Chen ... Xu Cheng Zhiqi Huang Bryan Hooi Stan Z. Li Keqin Li LLMAG LRM 500 49 0 29 Mar 2025
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond Xiaoye Qu Yafu Li Zhaochen Su Weigao Sun Jianhao Yan ... Chaochao Lu Yue Zhang Xian-Sheng Hua Bowen Zhou Yu Cheng ReLM OffRL LRM 446 98 0 27 Mar 2025
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Yang Sui Yu-Neng Chuang Guanchu Wang Jiamu Zhang Tianyi Zhang ... Andrew Wen Shaochen Zhong Hanjie Chen Helen Zhou OffRL ReLM LRM 680 254 0 20 Mar 2025
InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models Yuchen Yan Yongliang Shen Yuhang Liu Jin Jiang Hao Fei Jian Shao Yueting Zhuang LRM ReLM 480 27 0 09 Mar 2025
DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models Yi Shen Jing Zhang Jieyun Huang Shuming Shi Wenjing Zhang Jiangze Yan Rongjia Du Ning Wang Kai Wang Shiguo Lian LRM 461 112 0 06 Mar 2025
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning Haotian Luo Li Shen Haiying He Yun Wang Shiwei Liu Wei Li Naiqiang Tan Xiaochun Cao Dacheng Tao VLM LRM 455 178 0 22 Jan 2025
Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost Sania Nayab Giulio Rossolini Giorgio Buttazzo Nicolamaria Manes F. Giacomelli Nicolamaria Manes Fabrizio Giacomelli LRM 365 76 0 29 Jul 2024
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Zefan Cai Yichi Zhang Bofei Gao Yuliang Liu Yongqian Li ... Wayne Xiong Yue Dong Baobao Chang Junjie Hu Wen Xiao 645 172 0 04 Jun 2024