Tootfinder

Reinforcement Learning in Vision: A Survey
Weijia Wu, Chen Gao, Joya Chen, Kevin Qinghong Lin, Qingwei Meng, Yiming Zhang, Yuke Qiu, Hong Zhou, Mike Zheng Shou
https://arxiv.org/abs/2508.08189

Reinforcement Learning in Vision: A Survey
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 up-to-date synthesis of the field. We first formalize visual RL problems and trace the evolution of policy-optimization strategies from RLHF to verifiable reward paradigms, and from Proximal Policy Optimization to Group Relative Policy Optimization. We then org…

Generating Query-Relevant Document Summaries via Reinforcement Learning
Nitin Yadav, Changsung Kang, Hongwei Shang, Ming Sun
https://arxiv.org/abs/2508.08404 https://

Generating Query-Relevant Document Summaries via Reinforcement Learning
E-commerce search engines often rely solely on product titles as input for ranking models with latency constraints. However, this approach can result in suboptimal relevance predictions, as product titles often lack sufficient detail to capture query intent. While product descriptions provide richer information, their verbosity and length make them unsuitable for real-time ranking, particularly for computationally expensive architectures like cross-encoder ranking models. To address this challe…

Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
Jia Fu, Xinyu Yang, Hongzhi Zhang, Yahui Liu, Jingyuan Zhang, Qi Wang, Fuzheng Zhang, Guorui Zhou
https://arxiv.org/abs/2508.05710

Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
Precise, correct feedback is crucial for effectively training large language models (LLMs) in code reinforcement learning. However, synthesizing high-quality test cases remains a profoundly challenging and unsolved problem. In this work, we present Klear-CodeTest, a comprehensive test case synthesis framework featuring rigorous verification to ensure quality and reliability of test cases. Our approach achieves broad coverage of programming problems via a novel Generator-Validation (G-V) framewo…

Deep Reinforcement Learning-Based Control Strategy with Direct Gate Control for Buck Converters
Noboru Katayama
https://arxiv.org/abs/2508.07693 https://ar…

Deep Reinforcement Learning-Based Control Strategy with Direct Gate Control for Buck Converters
This paper proposes a deep reinforcement learning (DRL)-based approach for directly controlling the gate signals of switching devices to achieve voltage regulation in a buck converter. Unlike conventional control methods, the proposed method directly generates gate signals using a neural network trained through DRL, with the objective of achieving high control speed and flexibility while maintaining stability. Simulation results demonstrate that the proposed direct gate control (DGC) method ach…

Rethinking Verification for LLM Code Generation: From Generation to Testing
Zihan Ma, Taolin Zhang, Maosong Cao, Wenwei Zhang, Minnan Luo, Songyang Zhang, Kai Chen
https://arxiv.org/abs/2507.06920

Rethinking Verification for LLM Code Generation: From Generation to Testing
Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number of homogeneous test cases, resulting in subtle faults going undetected. This not only artificially inflates measured performance but also compromises accurate reward estimation in reinforcement learning frameworks utilizing verifiable rewards (RLVR). To addr…

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
Bingning Huang, Tu Nguyen, Matthieu Zimmer
https://arxiv.org/abs/2509.09284 https://

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning
Recent advances in reasoning with large language models (LLMs) have shown the effectiveness of Monte Carlo Tree Search (MCTS) for generating high-quality intermediate trajectories, particularly in math and symbolic domains. Inspired by this, we explore how MCTS-derived trajectories, traditionally used for training value or reward models, can be repurposed to improve policy optimization in preference-based reinforcement learning (RL). Specifically, we focus on Group Relative Policy Optimization …

RewardDance: Reward Scaling in Visual Generation
Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, Hanzhong Guo, Jie Liu, Zeyue Xue, Xiaoxia Hou, Wei Liu, Yan Zeng, Weilin Huang
https://arxiv.org/abs/2509.08826

RewardDance: Reward Scaling in Visual Generation
Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critical…

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
Yuqin Dai, Shuo Yang, Guoqing Wang, Yong Deng, Zhanwei Zhang, Jun Yin, Pengyu Zeng, Zhenzhe Ying, Changhua Meng, Can Yi, Yuchen Zhou, Weiqiang Wang, Shuai Lu
https://arxiv.org/abs/2508.07956…

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive misinformation in the web environment, which introduces unreliable or misleading content that can degrade retrieval accuracy, and the underutilization of web tools, which, if effectively employed, could enhance query precision and help mitigate this noise, ul…

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
Xinge Ye, Rui Wang, Yuchuan Wu, Victor Ma, Feiteng Fang, Fei Huang, Yongbin Li
https://arxiv.org/abs/2508.09074

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like role-playing dialogue. Traditional reward modeling approaches, which rely on independent sample-wise scoring, face dual challenges: subjective evaluation criteria and unstable reward signals.Motivated by the insight that human evaluation inherently combines explicit criteria with i…

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation
Zhiyou Xiao, Qinhan Yu, Binghui Li, Geng Chen, Chong Chen, Wentao Zhang
https://arxiv.org/abs/2508.06328

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation
Current research on Multimodal Retrieval-Augmented Generation (MRAG) enables diverse multimodal inputs but remains limited to single-modality outputs, restricting expressive capacity and practical utility. In contrast, real-world applications often demand both multimodal inputs and multimodal outputs for effective communication and grounded reasoning. Motivated by the recent success of Reinforcement Learning (RL) in complex reasoning tasks for Large Language Models (LLMs), we adopt RL as a prin…