中文
相关论文

相关论文: GTR: Guided Thought Reinforcement Prevents Thought…

200 篇论文

Reinforcement learning from verifiable rewards (RLVR) stimulates the thinking processes of large language models (LLMs), substantially enhancing their reasoning abilities on verifiable tasks. It is often assumed that similar gains should…

计算与语言 · 计算机科学 2026-03-24 Kaiyuan Li , Jing-Cheng Pang , Yang Yu

Reinforcement learning with verifiable reward (RLVR) has been instrumental in eliciting strong reasoning capabilities from large language models (LLMs) via long chains of thought (CoT). During RLVR training, we formalize and systemically…

计算与语言 · 计算机科学 2026-02-24 Cheonbok Park , Jeonghoon Kim , Joosung Lee , Sanghwan Bae , Jaegul Choo , Kang Min Yoo

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

人工智能 · 计算机科学 2024-10-10 Yuexiang Zhai , Hao Bai , Zipeng Lin , Jiayi Pan , Shengbang Tong , Yifei Zhou , Alane Suhr , Saining Xie , Yann LeCun , Yi Ma , Sergey Levine

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 --…

计算与语言 · 计算机科学 2025-09-25 Adithya Bhaskar , Xi Ye , Danqi Chen

Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant interest in the potential of Reinforcement Learning with…

人工智能 · 计算机科学 2025-10-03 Xumeng Wen , Zihan Liu , Shun Zheng , Shengyu Ye , Zhirong Wu , Yang Wang , Zhijian Xu , Xiao Liang , Junjie Li , Ziming Miao , Jiang Bian , Mao Yang

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulations typically treat exploration and consolidation as a…

机器学习 · 计算机科学 2026-05-15 Wenze Lin , Zhen Yang , Xitai Jiang , Xiaoteng Ma , Gao Huang

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…

人工智能 · 计算机科学 2025-10-30 Jiaqi Wang , Kevin Qinghong Lin , James Cheng , Mike Zheng Shou

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning performance of large language models (LLMs) by increasing test-time compute. However, even after extensive RLVR training, such models still…

人工智能 · 计算机科学 2026-03-10 Pinzheng Wang , Shuli Xu , Juntao Li , Yu Luo , Dong Li , Jianye Hao , Min Zhang

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

机器学习 · 计算机科学 2025-07-31 Zijing Zhang , Ziyang Chen , Mingxiao Li , Zhaopeng Tu , Xiaolong Li

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However, a critical…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Jinda Lu , Junkang Wu , Jinghan Li , Kexin Huang , Shuo Yang , Mingzhu Chen , Jiancan Wu , Kuien Liu , Xiang Wang

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…

计算与语言 · 计算机科学 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…

机器学习 · 计算机科学 2026-02-10 Hyunseok Lee , Soheil Abbasloo , Jihoon Tack , Jinwoo Shin

Multi-turn reinforcement learning (RL) for multi-modal agents built upon vision-language models (VLMs) is hampered by sparse rewards and long-horizon credit assignment. Recent methods densify the reward by querying a teacher that provides…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Tong Wei , Yijun Yang , Changhao Zhang , Junliang Xing , Yuanchun Shi , Zongqing Lu , Deheng Ye

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

人工智能 · 计算机科学 2026-01-19 Hongye Cao , Zhixin Bai , Ziyue Peng , Boyan Wang , Tianpei Yang , Jing Huo , Yuyao Zhang , Yang Gao

Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with…

机器学习 · 计算机科学 2026-05-29 Jonathan Williams , Esin Tureci

While reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs), its reliance on human-annotated labels leads to the scaling up dilemma, especially for complex tasks.…

机器学习 · 计算机科学 2026-03-17 Zizhuo Zhang , Jianing Zhu , Xinmu Ge , Zihua Zhao , Zhanke Zhou , Xuan Li , Xiao Feng , Jiangchao Yao , Bo Han

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short…

人工智能 · 计算机科学 2024-10-22 Ruohong Zhang , Bowen Zhang , Yanghao Li , Haotian Zhang , Zhiqing Sun , Zhe Gan , Yinfei Yang , Ruoming Pang , Yiming Yang

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However,…

机器学习 · 计算机科学 2025-08-28 Zhiwei Li , Yong Hu , Wenqing Wang

Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs). However, due to the complexity of multimodal scenarios and the difficulty in collecting high-quality CoT data, CoT reasoning in…

机器学习 · 计算机科学 2024-11-05 Kanzhi Cheng , Yantao Li , Fangzhi Xu , Jianbing Zhang , Hao Zhou , Yang Liu

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Yanbei Jiang , Chao Lei , Yihao Ding , Krista Ehinger , Jey Han Lau
‹ 上一页 1 2 3 10 下一页 ›