English
Related papers

Related papers: SPINE: Token-Selective Test-Time Reinforcement Lea…

200 papers

Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Akshit Singh , Shyam Marjit , Wei Lin , Paul Gavrikov , Serena Yeung-Levy , Hilde Kuehne , Rogerio Feris , Sivan Doveh , James Glass , M. Jehanzeb Mirza

Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test data without access to labels. However, this reliance on…

Machine Learning · Computer Science 2026-03-17 Vanshaj Khattar , Md Rafi ur Rashid , Moumita Choudhury , Jing Liu , Toshiaki Koike-Akino , Ming Jin , Ye Wang

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference…

Computation and Language · Computer Science 2026-02-03 Zimeng Wu , Donghao Wang , Chaozhe Jin , Jiaxin Chen , Yunhong Wang

Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks. While methods like Chain-of-Thought (CoT) reasoning and enhance LLM performance by decomposing problems into intermediate steps, they also incur…

Computation and Language · Computer Science 2025-06-03 Tingxu Han , Zhenting Wang , Chunrong Fang , Shiyu Zhao , Shiqing Ma , Zhenyu Chen

Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently…

Computation and Language · Computer Science 2024-11-19 Sreeram Vennam , David Valente , David Herel , Ponnurangam Kumaraguru

Eliciting explicit, step-by-step reasoning traces from large language models (LLMs) has emerged as a dominant paradigm for enhancing model capabilities. Although such reasoning strategies were originally designed for problems requiring…

Computation and Language · Computer Science 2026-03-23 Xinyu Guo , Yazhou Zhang , Jing Qin

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Computation and Language · Computer Science 2024-06-18 Zhipeng Chen , Kun Zhou , Wayne Xin Zhao , Junchen Wan , Fuzheng Zhang , Di Zhang , Ji-Rong Wen

Chain-of-thought (CoT) enhances the problem-solving ability of large language models (LLMs) but incurs substantial inference cost due to long autoregressive trajectories. Existing acceleration strategies either shorten traces via early…

Machine Learning · Computer Science 2026-02-10 Zhuokun Chen , Zeren Chen , Jiahao He , Lu Sheng , Mingkui Tan , Jianfei Cai , Bohan Zhuang

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…

Computation and Language · Computer Science 2025-08-14 Yue Liu , Jiaying Wu , Yufei He , Ruihan Gong , Jun Xia , Liang Li , Hongcheng Gao , Hongyu Chen , Baolong Bi , Jiaheng Zhang , Zhiqi Huang , Bryan Hooi , Stan Z. Li , Keqin Li

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…

Test-time scaling has enabled Large Language Models (LLMs) to tackle complex reasoning, yet the limitations of current Chain-of-Thought (CoT) evaluation obscures whether performance gains stem from genuine reasoning or mere verbosity. To…

Artificial Intelligence · Computer Science 2026-01-08 Zhizhang Fu , Yuancheng Gu , Chenkai Hu , Hanmeng Liu , Yue Zhang

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with…

Machine Learning · Computer Science 2025-06-03 Weizhe Lin , Xing Li , Zhiyuan Yang , Xiaojin Fu , Hui-Ling Zhen , Yaoyuan Wang , Xianzhi Yu , Wulong Liu , Xiaosong Li , Mingxuan Yuan

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

Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for…

Computation and Language · Computer Science 2025-10-06 Jian Mu , Qixin Zhang , Zhiyong Wang , Menglin Yang , Shuang Qiu , Chengwei Qin , Zhongxiang Dai , Yao Shu

Test-Time Scaling (TTS) has emerged as an effective paradigm for improving the reasoning performance of large language models (LLMs). However, existing methods -- most notably majority voting and heuristic token-level scoring -- treat…

Computation and Language · Computer Science 2026-02-03 Kai Zhang , Jiayi Liao , Chengpeng Li , Ziyuan Xie , Sihang Li , Xiang Wang

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…

Computation and Language · Computer Science 2026-02-05 Zihan Lin , Xiaohan Wang , Jie Cao , Jiajun Chai , Guojun Yin , Wei Lin , Ran He

Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language tokens with continuous latent tokens. These methods consume fewer tokens…

Artificial Intelligence · Computer Science 2026-01-30 Zhi Zheng , Wee Sun Lee

Reinforcement learning with verifiable rewards (RLVR) has shown great promise in enhancing the reasoning abilities of large reasoning models (LRMs). However, it suffers from a critical issue: entropy collapse and premature convergence.…

Machine Learning · Computer Science 2025-09-30 Yuxian Jiang , Yafu Li , Guanxu Chen , Dongrui Liu , Yu Cheng , Jing Shao

Existing test-time scaling (TTS) methods for unified multimodal models (UMMs) in text-to-image (T2I) generation primarily rely on search or sampling strategies that produce only instance-level improvements, limiting the ability to learn…

Machine Learning · Computer Science 2026-03-18 Lit Sin Tan , Junzhe Chen , Xiaolong Fu , Lichen Ma , Junshi Huang , Jianzhong Shi , Yan Li , Lijie Wen

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Computation and Language · Computer Science 2025-06-24 Kang Chen , Mengdi Zhang , Yixin Cao
‹ Prev 1 3 4 5 6 7 10 Next ›