Built on

Distilling the knowledge in a neural network
Original
Geoffrey Hinton, Oriol Vinyals, and Jeff Dean · 2015
Earlier work this paper cites.
Megatron-lm: Training multi-billion parameter language models using model parallelism
Original
Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro · 2019
Earlier work this paper cites.
Training verifiers to solve math word problems
Original
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman · 2021
Earlier work this paper cites.
Measuring mathematical problem solving with the math dataset
Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt · 2021
Earlier work this paper cites.
Teaching small language models to reason
Original
Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, and Aliaksei Severyn · 2022
Earlier work this paper cites.
Chain-of-thought prompting elicits reasoning in large language models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al · 2022
Earlier work this paper cites.
Mixed distillation helps smaller language model better reasoning
Original
Chenglin Li, Qianglong Chen, Liangyue Li, Caiyu Wang, Yicheng Li, Zulong Chen, and Yin Zhang · 2023
Earlier work this paper cites.
Let’s verify step by step
Original
Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe · 2023
Earlier work this paper cites.
Aime problem set 1983-2024, 2023
Hemish Veeraboina · 2023
Earlier work this paper cites.
Distilling reasoning ability from large language models with adaptive thinking
Original
Xiaoshu Chen, Sihang Zhou, Ke Liang, and Xinwang Liu · 2024
Earlier work this paper cites.
Do not think that much for 2+ 3=? on the overthinking of o1-like llms
Original
Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, et al · 2024
Earlier work this paper cites.
Token-budget-aware llm reasoning
Original
Tingxu Han, Zhenting Wang, Chunrong Fang, Shiyu Zhao, Shiqing Ma, and Zhenyu Chen · 2024
Earlier work this paper cites.
Openai o1 system card
Original
Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al · 2024
Earlier work this paper cites.
C3ot: Generating shorter chain-of-thought without compromising effectiveness
Original
Yu Kang, Xianghui Sun, Liangyu Chen, and Wei Zou · 2024
Earlier work this paper cites.
Routellm: Learning to route llms with preference data
Original
Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E Gonzalez, M Waleed Kadous, and Ion Stoica · 2024
Earlier work this paper cites.

Similar

Deepseekmath: Pushing the limits of mathematical reasoning in open language models
Original
Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al · 2024
Cited alongside, same era.
Hybridflow: A flexible and efficient rlhf framework
Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu · 2024
Cited alongside, same era.
Qwen2. 5 technical report
Original
An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al · 2024
Cited alongside, same era.
Distilling system 2 into system 1
Original
Ping Yu, Jing Xu, Jason Weston, and Ilia Kulikov · 2024
Cited alongside, same era.
Improving mathematical reasoning capabilities of small language models via feedback-driven distillation

Then

Small models struggle to learn from strong reasoners
Original
Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, and Radha Poovendran · 2025
Closest in time.
Reward-guided speculative decoding for efficient llm reasoning
Original
Baohao Liao, Yuhui Xu, Hanze Dong, Junnan Li, Christof Monz, Silvio Savarese, Doyen Sahoo, and Caiming Xiong · 2025
Closest in time.
Understanding r1-zero-like training: A critical perspective
Original
Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin · 2025
Closest in time.
O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning
Original
Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao · 2025
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2025

Thinkless: LLM Learns When to Think

Fang, Gongfan, Ma, Xinyin, Wang, Xinchao

Understand

Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference.

However, applying elaborate reasoning for all queries often results in substantial computational inefficiencies, particularly when many problems admit straightforward solutions.
This motivates an open question: Can LLMs learn when to think? To answer this, we propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning, based on both task complexity and the model's ability.
Thinkless is trained under a reinforcement learning paradigm and employs two control tokens, <short> for concise responses and <think> for detailed reasoning.

Built on

Distilling the knowledge in a neural network
Original
Geoffrey Hinton, Oriol Vinyals, and Jeff Dean · 2015
Earlier work this paper cites.
Megatron-lm: Training multi-billion parameter language models using model parallelism
Original
Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro · 2019
Earlier work this paper cites.
Training verifiers to solve math word problems
Original
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman · 2021
Earlier work this paper cites.
Measuring mathematical problem solving with the math dataset
Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt · 2021
Earlier work this paper cites.
Teaching small language models to reason
Original
Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, and Aliaksei Severyn · 2022
Earlier work this paper cites.
Chain-of-thought prompting elicits reasoning in large language models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al · 2022
Earlier work this paper cites.
Mixed distillation helps smaller language model better reasoning
Original
Chenglin Li, Qianglong Chen, Liangyue Li, Caiyu Wang, Yicheng Li, Zulong Chen, and Yin Zhang · 2023
Earlier work this paper cites.
Let’s verify step by step
Original
Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe · 2023
Earlier work this paper cites.
Aime problem set 1983-2024, 2023
Hemish Veeraboina · 2023
Earlier work this paper cites.
Distilling reasoning ability from large language models with adaptive thinking
Original
Xiaoshu Chen, Sihang Zhou, Ke Liang, and Xinwang Liu · 2024
Earlier work this paper cites.
Do not think that much for 2+ 3=? on the overthinking of o1-like llms
Original
Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, et al · 2024
Earlier work this paper cites.
Token-budget-aware llm reasoning
Original
Tingxu Han, Zhenting Wang, Chunrong Fang, Shiyu Zhao, Shiqing Ma, and Zhenyu Chen · 2024
Earlier work this paper cites.
Openai o1 system card
Original
Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al · 2024
Earlier work this paper cites.
C3ot: Generating shorter chain-of-thought without compromising effectiveness
Original
Yu Kang, Xianghui Sun, Liangyu Chen, and Wei Zou · 2024
Earlier work this paper cites.
Routellm: Learning to route llms with preference data
Original
Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E Gonzalez, M Waleed Kadous, and Ion Stoica · 2024
Earlier work this paper cites.

Similar

Deepseekmath: Pushing the limits of mathematical reasoning in open language models
Original
Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al · 2024
Cited alongside, same era.
Hybridflow: A flexible and efficient rlhf framework
Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu · 2024
Cited alongside, same era.
Qwen2. 5 technical report
Original
An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al · 2024
Cited alongside, same era.
Distilling system 2 into system 1
Original
Ping Yu, Jing Xu, Jason Weston, and Ilia Kulikov · 2024
Cited alongside, same era.
Improving mathematical reasoning capabilities of small language models via feedback-driven distillation

Then

Small models struggle to learn from strong reasoners
Original
Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, and Radha Poovendran · 2025
Closest in time.
Reward-guided speculative decoding for efficient llm reasoning
Original
Baohao Liao, Yuhui Xu, Hanze Dong, Junnan Li, Christof Monz, Silvio Savarese, Doyen Sahoo, and Caiming Xiong · 2025
Closest in time.
Understanding r1-zero-like training: A critical perspective
Original
Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin · 2025
Closest in time.
O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning
Original
Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao · 2025
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Original

Xunyu Zhu, Jian Li, Can Ma, and Weiping Wang · 2024

Cited alongside, same era.

L1: Controlling how long a reasoning model thinks with reinforcement learning

Original

Pranjal Aggarwal and Sean Welleck · 2025

Cited alongside, same era.

Claude 3.7 Sonnet

Anthropic · 2025

Cited alongside, same era.

Sketch-of-thought: Efficient llm reasoning with adaptive cognitive-inspired sketching

Original

Simon A Aytes, Jinheon Baek, and Sung Ju Hwang · 2025

Cited alongside, same era.

Research: Learning to reason with search for llms via reinforcement learning

Original

Mingyang Chen, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z Pan, Wen Zhang, Huajun Chen, Fan Yang, et al · 2025

Cited alongside, same era.

The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks

Original

Alejandro Cuadron, Dacheng Li, Wenjie Ma, Xingyao Wang, Yichuan Wang, Siyuan Zhuang, Shu Liu, Luis Gaspar Schroeder, Tian Xia, Huanzhi Mao, et al · 2025

Cited alongside, same era.

Open r1: A fully open reproduction of deepseek-r1, January 2025

Hugging Face · 2025

Cited alongside, same era.

Efficient reasoning models: A survey

Original

Sicheng Feng, Gongfan Fang, Xinyin Ma, and Xinchao Wang · 2025

Cited alongside, same era.

Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl

Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, et al · 2025

Closest in time.

Cot-valve: Length-compressible chain-of-thought tuning