English
Related papers

Related papers: Evolving Language Models without Labels: Majority …

200 papers

Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing remedies such as…

Artificial Intelligence · Computer Science 2026-04-17 Zhuo Wang , Zhuo Zhang , Yafu Li , Yu Cheng , Lizhen Qu , Zenglin Xu

Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore), a structured…

Artificial Intelligence · Computer Science 2025-07-10 Tianyu Zheng , Tianshun Xing , Qingshui Gu , Taoran Liang , Xingwei Qu , Xin Zhou , Yizhi Li , Zhoufutu Wen , Chenghua Lin , Wenhao Huang , Qian Liu , Ge Zhang , Zejun Ma

Recent advances in large language models (LLMs) have highlighted the potential of reinforcement learning with verifiable rewards (RLVR) to enhance reasoning capabilities through extended output sequences. However, traditional RL frameworks…

Computation and Language · Computer Science 2025-07-29 Dong Du , Shulin Liu , Tao Yang , Shaohua Chen , Yang Li

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…

The use of large language models (LLMs) as automated evaluation tools to assess the quality of generated natural language, known as LLMs-as-Judges, has demonstrated promising capabilities and is rapidly gaining widespread attention.…

Computation and Language · Computer Science 2024-10-22 Haitao Li , Junjie Chen , Qingyao Ai , Zhumin Chu , Yujia Zhou , Qian Dong , Yiqun Liu

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation…

Machine Learning · Computer Science 2025-06-24 Tianyu Yu , Bo Ji , Shouli Wang , Shu Yao , Zefan Wang , Ganqu Cui , Lifan Yuan , Ning Ding , Yuan Yao , Zhiyuan Liu , Maosong Sun , Tat-Seng Chua

Recently, numerous new benchmarks have been established to evaluate the performance of large language models (LLMs) via either computing a holistic score or employing another LLM as a judge. However, these approaches suffer from data…

Computation and Language · Computer Science 2024-12-16 Xiang Li , Yunshi Lan , Chao Yang

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider…

Machine Learning · Computer Science 2025-09-25 Guochao Jiang , Wenfeng Feng , Guofeng Quan , Chuzhan Hao , Yuewei Zhang , Guohua Liu , Hao Wang

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. As a…

Computation and Language · Computer Science 2024-01-02 Yihan Chen , Benfeng Xu , Quan Wang , Yi Liu , Zhendong Mao

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

Machine Learning · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Xiangyuan Lan , Dongbin Zhao

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve…

Computation and Language · Computer Science 2025-12-16 Xiao Liang , Zhongzhi Li , Yeyun Gong , Yelong Shen , Ying Nian Wu , Zhijiang Guo , Weizhu Chen

Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative…

Machine Learning · Computer Science 2026-05-11 Zihan Lin , Xiaohan Wang , Jie Cao , Jiajun Chai , Li Wang , Xiaodong Lu , Wei Lin , Ran He , Guojun Yin

Although Large Audio-Language Models (LALMs) have exhibited outstanding performance in auditory understanding, their performance in affective computing scenarios, particularly in emotion recognition, reasoning, and subtle sentiment…

Sound · Computer Science 2025-09-23 Pengcheng Li , Botao Zhao , Zuheng Kang , Junqing Peng , Xiaoyang Qu , Yayun He , Jianzong Wang

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

Machine Learning · Computer Science 2026-05-19 Chen Wang , Zhaochun Li , Jionghao Bai , Hexuan Deng , Ge Lan , Yue Wang

Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are estimated without ground-truth supervision. Most existing…

Computation and Language · Computer Science 2026-01-30 Bodong Du , Xuanqi Huang , Xiaomeng Li

It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to diversity collapse, where outputs lack variety. Prior work has proposed a range of heuristics to counteract this effect, but these…

Machine Learning · Computer Science 2025-12-12 Jingchu Gai , Guanning Zeng , Huaqing Zhang , Aditi Raghunathan

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) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced with spurious prompt-level cues such as consensus claims or…

Computers and Society · Computer Science 2026-04-07 Qian Wang , Xuandong Zhao , Zirui Zhang , Zhanzhi Lou , Nuo Chen , Dawn Song , Bingsheng He

Zero Reinforcement Learning (Zero-RL) has proven to be an effective approach for enhancing the reasoning capabilities of large language models (LLMs) by directly applying reinforcement learning with verifiable rewards on pretrained models,…

Artificial Intelligence · Computer Science 2025-10-30 Yuyuan Zeng , Yufei Huang , Can Xu , Qingfeng Sun , Jianfeng Yan , Guanghui Xu , Tao Yang , Fengzong Lian

Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals…

Computation and Language · Computer Science 2026-04-15 Qingyu Ren , Qianyu He , Powei Chang , Jie Zeng , Zeye Sun , Fei Yu , Jiaqing Liang , Yanghua Xiao