English
Related papers

Related papers: e1: Learning Adaptive Control of Reasoning Effort

200 papers

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Large language models (LLMs) are increasingly being deployed in cost and latency-sensitive settings. While chain-of-thought improves reasoning, it can waste tokens on simple requests. We study selective thinking for tool-using LLMs and…

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

Large Language Models (LLMs) are pivotal in advancing natural language processing but often struggle with complex reasoning tasks due to inefficient attention distributions. In this paper, we explore the effect of increased computed tokens…

Computation and Language · Computer Science 2024-06-25 Bingli Liao , Danilo Vasconcellos Vargas

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce…

Artificial Intelligence · Computer Science 2026-04-10 Zhicheng Yang , Zhijiang Guo , Yinya Huang , Yongxin Wang , Wenlei Shi , Yiwei Wang , Xiaodan Liang , Jing Tang

Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the…

Computation and Language · Computer Science 2016-11-17 Mark Neumann , Pontus Stenetorp , Sebastian Riedel

Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with…

Machine Learning · Computer Science 2026-03-10 Hejian Sang , Yuanda Xu , Zhengze Zhou , Ran He , Zhipeng Wang

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Computation and Language · Computer Science 2026-05-12 Ömer Faruk Akgül , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

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) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…

Machine Learning · Computer Science 2026-02-10 Srijan Shakya , Anamaria-Roberta Hartl , Sepp Hochreiter , Korbinian Pöppel

In order to address the chain of thought in the large language model inference cost surge, this research proposes to use a sparse attention mechanism that only focuses on a few relevant tokens. The researcher constructed a new attention…

Machine Learning · Computer Science 2025-07-11 Libo Wang

Chain-of-Thought (CoT) prompting improves reasoning but often produces long and redundant traces that substantially increase inference cost. We present SyncThink, a training-free and plug-and-play decoding method that reduces CoT overhead…

Computation and Language · Computer Science 2026-01-08 Gengyang Li , Wang Cai , Yifeng Gao , Yunfang Wu

Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text tokens. However, this results in lengthy inputs where many words…

Computation and Language · Computer Science 2025-09-03 DiJia Su , Hanlin Zhu , Yingchen Xu , Jiantao Jiao , Yuandong Tian , Qinqing Zheng

Modern causal language models, followed by rapid developments in discrete diffusion models, can now produce a wide variety of interesting and useful content. However, these families of models are predominantly trained to output tokens with…

Computation and Language · Computer Science 2025-08-19 Long Ma , Fangwei Zhong , Yizhou Wang

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks but come with substantial energy and computational costs, particularly in request-heavy scenarios. In many real-world applications, the full scale and…

Computation and Language · Computer Science 2026-03-24 Patrick Wilhelm , Thorsten Wittkopp , Odej Kao

Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek R1) have led to a popular belief that extending thinking traces using prompts like "Wait" or "Let me rethink" can improve performance. This raises a natural…

Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by prompting intermediate steps, improving accuracy and robustness in arithmetic, logic, and commonsense tasks. However, this benefit comes with high computational…

Software Engineering · Computer Science 2026-03-11 Kerui Huang , Shuhan Liu , Xing Hu , Tongtong Xu , Lingfeng Bao , Xin Xia

Executing workflows on volunteer computing resources where individual tasks may be forced to relinquish their resource for the resource's primary use leads to unpredictability and often significantly increases execution time. Task…

Performance · Computer Science 2022-09-28 Andrew Stephen McGough , Matthew Forshaw

Large language models trained with reinforcement learning with verifiable rewards tend to trade accuracy for length--inflating response lengths to achieve gains in accuracy. While longer answers may be warranted for harder problems, many…

Computation and Language · Computer Science 2025-08-14 Vaishnavi Shrivastava , Ahmed Awadallah , Vidhisha Balachandran , Shivam Garg , Harkirat Behl , Dimitris Papailiopoulos

A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesized by strong Large Reasoning Models such as DeepSeek-R1,…

Computation and Language · Computer Science 2025-12-24 Cehao Yang , Xueyuan Lin , Xiaojun Wu , Chengjin Xu , Xuhui Jiang , Honghao Liu , Hui Xiong , Jian Guo