English
Related papers

Related papers: Controllable Mathematical Reasoning via Self-Optim…

200 papers

Recent advancements in Large Language Models (LLMs) have sparked interest in their formal reasoning capabilities, particularly in mathematics. The GSM8K benchmark is widely used to assess the mathematical reasoning of models on…

Machine Learning · Computer Science 2025-08-28 Iman Mirzadeh , Keivan Alizadeh , Hooman Shahrokhi , Oncel Tuzel , Samy Bengio , Mehrdad Farajtabar

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Computation and Language · Computer Science 2025-08-11 Ruosen Li , Ziming Luo , Quan Zhang , Ruochen Li , Ben Zhou , Ali Payani , Xinya Du

Large language models (LLMs) often struggle with maintaining accuracy throughout multiple multiple reasoning steps, especially in mathematical reasoning where an error in earlier steps can propagate to subsequent ones and it ultimately…

Artificial Intelligence · Computer Science 2024-04-02 Fei Yu , Anningzhe Gao , Benyou Wang

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing

To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabilities, it is difficult or impossible to get high-quality…

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress…

Computation and Language · Computer Science 2026-04-07 Yuqi Zhu , Jintian Zhang , Zhenjie Wan , Yujie Luo , Shuofei Qiao , Zhengke Gui , Da Zheng , Lei Liang , Huajun Chen , Ningyu Zhang

This paper presents a novel operator-theoretic approach for optimal control of nonlinear stochastic systems within reproducing kernel Hilbert spaces. Our learning framework leverages data samples of system dynamics and stage cost functions,…

Optimization and Control · Mathematics 2025-04-28 Petar Bevanda , Nicolas Hoischen , Tobias Wittmann , Jan Brüdigam , Sandra Hirche , Boris Houska

Through reinforcement learning with verifiable rewards (RLVR), large language models have achieved substantial progress in domains with easily verifiable outcomes, such as mathematics and coding. However, when applied to more complex tasks…

Computation and Language · Computer Science 2025-10-01 Qiyao Ma , Yunsheng Shi , Hongtao Tian , Chao Wang , Weiming Chang , Ting Yao

Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. When moving beyond prompting, this raises the question of how we should supervise such models: outcome-based…

Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free…

Computation and Language · Computer Science 2025-04-18 Wang Yang , Xiang Yue , Vipin Chaudhary , Xiaotian Han

Reinforcement learning with verifiable rewards (RLVR) improves language model reasoning by using rule-based rewards in verifiable domains such as mathematics and code. However, RLVR leads to limited generalization for open-ended tasks --…

Computation and Language · Computer Science 2025-09-25 Adithya Bhaskar , Xi Ye , Danqi Chen

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

Computation and Language · Computer Science 2026-03-03 David Bani-Harouni , Chantal Pellegrini , Paul Stangel , Ege Özsoy , Kamilia Zaripova , Nassir Navab , Matthias Keicher

Recent advancements in Multimodal Large Language Models (MLLMs), particularly through Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced their reasoning abilities. However, a critical gap persists: these…

Artificial Intelligence · Computer Science 2025-07-14 Inclusion AI , : , Fudong Wang , Jiajia Liu , Jingdong Chen , Jun Zhou , Kaixiang Ji , Lixiang Ru , Qingpei Guo , Ruobing Zheng , Tianqi Li , Yi Yuan , Yifan Mao , Yuting Xiao , Ziping Ma

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

Computation and Language · Computer Science 2026-03-09 Xiusi Chen , Gaotang Li , Ziqi Wang , Bowen Jin , Cheng Qian , Yu Wang , Hongru Wang , Yu Zhang , Denghui Zhang , Tong Zhang , Hanghang Tong , Heng Ji

Past vocabulary learning techniques identify relevant vocabulary before training, relying on statistical and entropy-based assumptions that largely neglect the role of model training. Empirically, we observe that trained translation models…

Computation and Language · Computer Science 2025-04-02 Pin-Jie Lin , Ernie Chang , Yangyang Shi , Vikas Chandra

Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B)…

Machine Learning · Computer Science 2026-03-05 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Reasoning large language models achieve impressive test-time scaling by thinking for longer, but this performance gain comes at significant compute cost. Directly limiting test-time budget hurts overall performance, but not all problems are…

Machine Learning · Computer Science 2025-05-27 Menghua Wu , Cai Zhou , Stephen Bates , Tommi Jaakkola

Thinking aloud is an effective meta-cognitive strategy human reasoners apply to solve difficult problems. We suggest to improve the reasoning ability of pre-trained neural language models in a similar way, namely by expanding a task's…

Computation and Language · Computer Science 2021-03-25 Gregor Betz , Kyle Richardson , Christian Voigt

Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervision. To address this issue, recent studies have explored…

Machine Learning · Computer Science 2025-05-26 Hyosoon Jang , Yunhui Jang , Sungjae Lee , Jungseul Ok , Sungsoo Ahn