English
Related papers

Related papers: Mid-Think: Training-Free Intermediate-Budget Reaso…

200 papers

Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over when to expand, what to prune, how to repair, and when to…

Artificial Intelligence · Computer Science 2026-03-31 Siyuan Ma , Bo Gao , Zikai Xiao , Hailong Wang , Xinlei Yu , Rui Qian , Jiayu Qian , Luqi Gong , Yang Liu

Large reasoning models (LRMs) have led to new possibilities in terms of problem-solving, through the devising of a natural language thought process prior to answering a query. While their capabilities are well known across mathematics and…

Computation and Language · Computer Science 2025-10-15 Armel Zebaze , Rachel Bawden , Benoît Sagot

Test-time scaling has emerged as a widely adopted inference-time strategy for boosting reasoning performance. However, its effectiveness has been studied almost exclusively in English, leaving its behavior in other languages largely…

Computation and Language · Computer Science 2025-05-22 Prasoon Bajpai , Tanmoy Chakraborty

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Computation and Language · Computer Science 2024-12-03 Oliver Kramer , Jill Baumann

We introduce a simple, yet novel entropy-based framework to drive token efficiency in large language models during reasoning tasks. Our approach uses Shannon entropy from token-level logprobs as a confidence signal to enable early stopping,…

Machine Learning · Computer Science 2025-10-29 Aman Sharma , Paras Chopra

We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thinking. During RL training, we observe an approximately…

Computation and Language · Computer Science 2026-04-03 Qianfan Zhang , Tianyu Guo , Xuandi Ren , Jiale Chen , Ming Ding , Ran Xin , Xia Xiao

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token costs. In this paper, we propose an efficient test-time…

Computation and Language · Computer Science 2025-04-02 Zhaojian Yu , Yinghao Wu , Yilun Zhao , Arman Cohan , Xiao-Ping Zhang

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 language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Artificial Intelligence · Computer Science 2026-02-03 Katrina Brown , Aneesh Muppidi , Rana Shahout

Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a…

Computation and Language · Computer Science 2026-04-21 Sangjun Song , Minjae Oh , Seungkyu Lee , Sungmin Jo , Yohan Jo

Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let…

Computation and Language · Computer Science 2024-04-23 Sachin Goyal , Ziwei Ji , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar , Vaishnavh Nagarajan

Large language models (LLMs) have scaled up to unlock a wide range of complex reasoning tasks with the aid of various prompting methods. However, current prompting methods generate natural language intermediate steps to help reasoning,…

Computation and Language · Computer Science 2023-10-10 Yi Hu , Haotong Yang , Zhouchen Lin , Muhan Zhang

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to…

Artificial Intelligence · Computer Science 2025-10-30 Jiaqi Wang , Kevin Qinghong Lin , James Cheng , Mike Zheng Shou

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

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value…

Artificial Intelligence · Computer Science 2025-11-13 Michael Kleinman , Matthew Trager , Alessandro Achille , Wei Xia , Stefano Soatto

We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…

Computation and Language · Computer Science 2025-12-01 Mukul Singh , Ananya Singha , Arjun Radhakrishna , Sumit Gulwani

Recent advances in large language models (LLMs) have leveraged explicit Chain-of-Thought (CoT) prompting to improve reasoning accuracy. However, most existing methods primarily focus on compressing verbose reasoning outputs. These…

Computation and Language · Computer Science 2025-12-01 Canhui Wu , Qiong Cao , Chao Xue , Wei Xi , Xiaodong He

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-06-10 Lennart Meincke , Ethan Mollick , Lilach Mollick , Dan Shapiro

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Computation and Language · Computer Science 2025-11-14 Mingye Zhu , Yi Liu , Zheren Fu , Quan Wang , Yongdong Zhang