English
Related papers

Related papers: Not All Turns Are Equally Hard: Adaptive Thinking …

200 papers

Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard questions remain under-explored. We propose Uncertainty-Aware Budget Allocation (UAB),…

Computation and Language · Computer Science 2026-05-27 Manh Nguyen , Sunil Gupta , Hung Le

Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance. Yet deploying these…

Machine Learning · Computer Science 2026-04-17 Zhiyuan Zhai , Bingcong Li , Bingnan Xiao , Ming Li , Xin Wang

Effective information seeking in multi-turn medical dialogues is critical for accurate diagnosis, especially when dealing with incomplete information. Aligning Large Language Models (LLMs) for these interactive scenarios is challenging due…

Machine Learning · Computer Science 2026-03-04 Ruike Cao , Shaojie Bai , Fugen Yao , Liang Dong , Jian Xu , Li Xiao

Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gains. Controlling…

Computation and Language · Computer Science 2025-06-17 Junyan Li , Wenshuo Zhao , Yang Zhang , Chuang Gan

Recent thinking models solve complex reasoning tasks by scaling test-time compute, but this scaling must be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require…

Machine Learning · Computer Science 2025-10-03 Joykirat Singh , Justin Chih-Yao Chen , Archiki Prasad , Elias Stengel-Eskin , Akshay Nambi , Mohit Bansal

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…

Computation and Language · Computer Science 2026-03-20 Arushi Rai , Qiang Zhang , Hanqing Zeng , Yunkai Zhang , Dipesh Tamboli , Xiangjun Fan , Zhuokai Zhao , Lizhu Zhang

Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning under tight compute and token budgets. Existing test time…

Computation and Language · Computer Science 2026-04-29 Sagnik Chatterjee , Atharva Patil , Sricharan Ramesh

Adaptive reasoning is essential for aligning the computational effort of large language models (LLMs) with the intrinsic difficulty of problems. Current chain-of-thought methods boost reasoning ability but indiscriminately generate long…

Artificial Intelligence · Computer Science 2025-12-17 Ruofan Zhang , Bin Xia , Zhen Cheng , Cairen Jian , Minglun Yang , Ngai Wong , Yuan Cheng

The cost of labeling data often limits the performance of machine learning systems. In multi-task learning, related tasks provide information to each other and improve overall performance, but the label cost can vary among tasks. How should…

Machine Learning · Computer Science 2023-08-25 Ximeng Sun , Kihyuk Sohn , Kate Saenko , Clayton Mellina , Xiao Bian

Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, existing approaches optimize reasoning under fixed or uniformly sampled token budgets,…

Computation and Language · Computer Science 2026-04-23 Amirul Rahman , Aisha Karim , Kenji Nakamura , Yi-Fan Ng

Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or thoughts, is rigid and unidirectional, such as chains, trees, or…

Artificial Intelligence · Computer Science 2024-12-30 Sijia Chen , Baochun Li

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate…

Machine Learning · Computer Science 2026-03-03 Junhong Lin , Xinyue Zeng , Jie Zhu , Song Wang , Julian Shun , Jun Wu , Dawei Zhou

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Computation and Language · Computer Science 2026-01-07 Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John , Michael Bohlke-Schneider , Momchil Hardalov

Solving mathematics problems has been an intriguing capability of large language models, and many efforts have been made to improve reasoning by extending reasoning length, such as through self-correction and extensive long…

Artificial Intelligence · Computer Science 2025-02-03 Zishun Yu , Tengyu Xu , Di Jin , Karthik Abinav Sankararaman , Yun He , Wenxuan Zhou , Zhouhao Zeng , Eryk Helenowski , Chen Zhu , Sinong Wang , Hao Ma , Han Fang

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world…

Software Engineering · Computer Science 2025-10-15 Marcus Emmanuel Barnes , Taher A. Ghaleb , Safwat Hassan

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

Machine Learning · Computer Science 2026-05-27 Alex Ayoub , Kavosh Asadi , Dale Schuurmans , Csaba Szepesvári , Karim Bouyarmane

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method…

Machine Learning · Computer Science 2025-09-23 Shuhao Jiang , Songbo Wang , Yang Qiao , Chun Xu , Chaoyang Zheng , Shengyi Zhou , Huanjun Wang , Fangming Li , Cong Zhang , Jiyu Wang

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individual outcomes.…

Artificial Intelligence · Computer Science 2025-05-19 Chan-Jan Hsu , Davide Buffelli , Jamie McGowan , Feng-Ting Liao , Yi-Chang Chen , Sattar Vakili , Da-shan Shiu

Chain-of-thought reasoning is often treated as a monotone way to improve language-model accuracy by letting a model think longer. We identify a countervailing effect, the coupling tax: when reasoning traces and final answers share one…

Machine Learning · Computer Science 2026-05-11 Wenhua Nie , Junlin Liu , Jianan Wu , Zijie Meng , Yilong Fan , Zhang Zijian , Haoran Zheng , Jyh-Shing Roger Jang