English
Related papers

Related papers: What If Consensus Lies? Selective-Complementary Re…

200 papers

Current label-free RLVR approaches for large language models (LLMs), such as TTRL and Self-reward, have demonstrated effectiveness in improving the performance of LLMs on complex reasoning tasks. However, these methods rely heavily on…

Machine Learning · Computer Science 2026-03-18 Kaixuan Du , Meng Cao , Hang Zhang , Yukun Wang , Xiangzhou Huang , Ni Li

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to…

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium…

Machine Learning · Computer Science 2026-04-24 Yongcan Yu , Lingxiao He , Jian Liang , Kuangpu Guo , Meng Wang , Qianlong Xie , Xingxing Wang , Ran He

Recent advances such as self-consistency and test-time reinforcement learning (TTRL) improve the reliability of large language models (LLMs) without additional supervision, yet their underlying mechanisms and statistical guarantees remain…

Machine Learning · Statistics 2025-10-24 Paula Cordero-Encinar , Andrew B. Duncan

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first,…

Machine Learning · Computer Science 2025-11-11 Peyman Hosseini , Ondrej Bohdal , Taha Ceritli , Ignacio Castro , Matthew Purver , Mete Ozay , Umberto Michieli

Test-time reinforcement learning (TTRL) has emerged as a promising paradigm for self-evolving large reasoning models (LRMs), enabling online adaptation on unlabeled test inputs via self-induced rewards through majority voting. However, a…

Artificial Intelligence · Computer Science 2026-03-03 Ruotong Liao , Nikolai Röhrich , Xiaohan Wang , Yuhui Zhang , Yasaman Samadzadeh , Volker Tresp , Serena Yeung-Levy

Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting (MV) as a heuristic supervision signal, which can be…

Machine Learning · Computer Science 2026-03-11 Kailong Fan , Anqi Pu , Yichen Wu , Wanhua Li , Yicong Li , Hanspeter Pfister , Huafeng Liu , Xiang Li , Quanzheng Li , Ning Guo

Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…

Computation and Language · Computer Science 2026-03-09 Jianghao Wu , Yasmeen George , Jin Ye , Yicheng Wu , Daniel F. Schmidt , Jianfei Cai

Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as pseudo-labels. However, we identify a critical failure mode:…

Computation and Language · Computer Science 2026-03-24 Teng Pan , Yuchen Yan , Zixuan Wang , Ruiqing Zhang , Guiyang Hou , Wenqi Zhang , Weiming Lu , Jun Xiao , Yongliang Shen

In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge in ICRL is reward estimation, as models typically lack…

Computation and Language · Computer Science 2026-04-02 Wenxuan Jiang , Yuxin Zuo , Zijian Zhang , Xuecheng Wu , Zining Fan , Wenxuan Liu , Li Chen , Xiaoyu Li , Xuezhi Cao , Xiaolong Jin , Ninghao Liu

Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority…

Computation and Language · Computer Science 2026-03-03 Ru Wang , Wei Huang , Qi Cao , Yusuke Iwasawa , Yutaka Matsuo , Jiaxian Guo

Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label signal. We argue these gains are systematically misinterpreted: most reflect sharpening of…

Machine Learning · Computer Science 2026-05-28 Hongxiang Lin , Zhirui Kuai , Erpeng Xue , Lei Wang

Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited…

Machine Learning · Computer Science 2025-09-01 Jia Liu , ChangYi He , YingQiao Lin , MingMin Yang , FeiYang Shen , ShaoGuo Liu

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Machine Learning · Computer Science 2025-10-06 Aleksei Arzhantsev , Otmane Sakhi , Flavian Vasile

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

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Artificial Intelligence · Computer Science 2025-08-11 Yihao Liu , Shuocheng Li , Lang Cao , Yuhang Xie , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Semi-supervised learning (SSL) has achieved great success in leveraging a large amount of unlabeled data to learn a promising classifier. A popular approach is pseudo-labeling that generates pseudo labels only for those unlabeled data with…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Qinyi Deng , Yong Guo , Zhibang Yang , Haolin Pan , Jian Chen

Large Audio Language Models (LALMs) demonstrate impressive general audio understanding, but once deployed, they are static and fail to improve with new real-world audio data. As traditional supervised fine-tuning is costly, we introduce a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-23 Haoyu Zhang , Jiaxian Guo , Yusuke Iwasawa , Yutaka Matsuo

Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard problems because correct final-answer rollouts are rare and sample-level credit assignment…

Machine Learning · Computer Science 2026-05-22 Xitai Jiang , Zihan Tang , Wenze Lin , Yang Yue , Shenzhi Wang , Gao Huang

Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable…

Computation and Language · Computer Science 2026-01-27 Wenkai Fang , Shunyu Liu , Yang Zhou , Kongcheng Zhang , Tongya Zheng , Kaixuan Chen , Mingli Song , Dacheng Tao
‹ Prev 1 2 3 10 Next ›