English
Related papers

Related papers: Visual Reasoning through Tool-supervised Reinforce…

200 papers

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, particularly in…

Computation and Language · Computer Science 2025-09-19 Weiting Tan , Xinghua Qu , Ming Tu , Meng Ge , Andy T. Liu , Philipp Koehn , Lu Lu

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Changpeng Wang , Haozhe Wang , Xi Chen , Junhan Liu , Taofeng Xue , Chong Peng , Donglian Qi , Fangzhen Lin , Yunfeng Yan

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Weijia Wu , Chen Gao , Joya Chen , Kevin Qinghong Lin , Qingwei Meng , Yiming Zhang , Yuke Qiu , Hong Zhou , Mike Zheng Shou

The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Haoji Zhang , Xin Gu , Jiawen Li , Chixiang Ma , Sule Bai , Chubin Zhang , Bowen Zhang , Zhichao Zhou , Dongliang He , Yansong Tang

Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL)…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Jie Yang , Feipeng Ma , Zitian Wang , Dacheng Yin , Kang Rong , Fengyun Rao , Ruimao Zhang

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essential for the success of RL. We observe that for complex…

Machine Learning · Computer Science 2025-07-08 Shihan Dou , Muling Wu , Jingwen Xu , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train…

Machine Learning · Computer Science 2025-11-11 Yirong Zeng , Xiao Ding , Yutai Hou , Yuxian Wang , Li Du , Juyi Dai , Qiuyang Ding , Duyu Tang , Dandan Tu , Weiwen Liu , Bing Qin , Ting Liu

In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models. The…

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…

Computation and Language · Computer Science 2025-06-02 Fei Bai , Yingqian Min , Beichen Zhang , Zhipeng Chen , Wayne Xin Zhao , Lei Fang , Zheng Liu , Zhongyuan Wang , Ji-Rong Wen

Visualization tools for supervised learning have allowed users to interpret, introspect, and gain intuition for the successes and failures of their models. While reinforcement learning practitioners ask many of the same questions, existing…

Machine Learning · Computer Science 2020-07-14 Shuby Deshpande , Jeff Schneider

Reinforcement learning has proven its effectiveness in enhancing the reasoning capabilities of large language models. Recent research efforts have progressively extended this paradigm to multimodal reasoning tasks. Due to the inherent…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Ruifeng Yuan , Chenghao Xiao , Sicong Leng , Jianyu Wang , Long Li , Weiwen Xu , Hou Pong Chan , Deli Zhao , Tingyang Xu , Zhongyu Wei , Hao Zhang , Yu Rong

Reinforcement learning (RL) problems can be challenging without well-shaped rewards. Prior work on provably efficient RL methods generally proposes to address this issue with dedicated exploration strategies. However, another way to tackle…

Machine Learning · Computer Science 2023-06-21 Qiyang Li , Yuexiang Zhai , Yi Ma , Sergey Levine

Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs…

Machine Learning · Computer Science 2025-04-07 Yan Ma , Steffi Chern , Xuyang Shen , Yiran Zhong , Pengfei Liu

Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe that in vision-dependent tasks, extended textual reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Soumya Suvra Ghosal , Youngeun Kim , Zhuowei Li , Ritwick Chaudhry , Linghan Xu , Hongjing Zhang , Jakub Zablocki , Yifan Xing , Qin Zhang

Video understanding is inherently intention-driven-humans naturally focus on relevant frames based on their goals. Recent advancements in multimodal large language models (MLLMs) have enabled flexible query-driven reasoning; however,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Ziqiang Xu , Qi Dai , Tian Xie , Yifan Yang , Kai Qiu , DongDong Chen , Zuxuan Wu , Chong Luo

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

Artificial Intelligence · Computer Science 2019-12-10 Allan Jabri , Kyle Hsu , Ben Eysenbach , Abhishek Gupta , Sergey Levine , Chelsea Finn

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

Machine Learning · Computer Science 2021-07-22 Karl Pertsch , Youngwoon Lee , Yue Wu , Joseph J. Lim

Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Chenghao Li , Fusheng Hao , Xikai Zhang , Likang Xiao , Yanwei Ren , Fuxiang Wu , Quan Chen , Liu Liu

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

Large language models (LLMs) have demonstrated strong capabilities in language understanding and reasoning, yet they remain limited when tackling real-world tasks that require up-to-date knowledge, precise operations, or specialized tool…

Machine Learning · Computer Science 2025-09-17 Yabo Zhang , Yihan Zeng , Qingyun Li , Zhen Hu , Kavin Han , Wangmeng Zuo