Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer rewards computed from the reasoning tokens can improve learning significantly by providing more fine-grained guidance. However, it is challenging to compute more informative rewards in MMRL beyond those based on outcomes since different samples may require different scoring functions and teacher models may provide noisy reward signals too. In this paper, we introduce the Argos (Agentic Reward for Grounded & Objective Scoring), a principled reward agent to train multimodal reasoning models for agentic tasks. For each sample, Argos selects from a pool of teacher-model derived and rule-based scoring functions to simultaneously evaluate: (i) final response accuracy, (ii) spatiotemporal localization of referred entities and actions, and (iii) the quality of the reasoning process. We find that by leveraging our agentic verifier across both SFT data curation and RL training, our model achieves state-of-the-art results across multiple agentic tasks such as spatial reasoning, visual hallucination as well as robotics and embodied AI benchmarks. Critically, we demonstrate that just relying on SFT post-training on highly curated reasoning data is insufficient, as agents invariably collapse to ungrounded solutions during RL without our online verification. We also show that our agentic verifier can help to reduce reward-hacking in MMRL. Finally, we also provide a theoretical justification for the effectiveness of Argos through the concept of pareto-optimality.
Rethinking Probability-Based Reinforcement Learning From Posterior Concentration
National University of Singapore（新加坡国立大学）；The Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology of China（中国科学技术大学）
CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving
State Key Laboratory of Networking and Switching Technology（网络与交换技术国家重点实验室）；School of Digital Media & Design Arts（数字媒体与设计艺术学院）；Beijing University of Posts and Telecommunications（北京邮电大学）
INESC-ID（里斯本高等理工学院信息技术与系统研究所）；Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等理工学院）；KTH Royal Institute of Technology（瑞典皇家理工学院）
This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions. To address such problem, we argue for hierarchy in the design of representation models and contribute with a novel multimodal representation model, MUSE. The proposed model learns hierarchical representations: low-level modality-specific representations, encoded from raw observation data, and a high-level multimodal representation, encoding joint-modality information to allow rob…
AgentV-RL: Scaling Reward Modeling with Agentic Verifier
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Huazhong University of Science and Technology（华中科技大学）；The University of Hong Kong（香港大学）；ByteDance Seed（字节跳动种子）；Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院）；Shanghai Key Laboratory of Multimodal Embodied AI（上海多模态具身人工智能重点实验室）
University of Science and Technology of China（中国科学技术大学）；Netease Fuxi AI Lab（网易伏羲人工智能实验室）
Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL) due to the heterogeneity and dynamic importance of different modalities. Specifically, we observe that these issues make conventional RL methods difficult to learn a useful state representation in the end-to-end training with multimodal information. To address this, we propose a novel multimodal RL approach that can do multimodal alignment and importance enha…
Coupled Variational Reinforcement Learning for Language Model General Reasoning
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室）；University of Chinese Academy of Sciences（中国科学院大学）
Aletheia: What Makes RLVR For Code Verifiers Tick?
INSAIT, Sofia University "St. Kliment Ohridski", Bulgaria（保加利亚索菲亚大学INSAIT实验室）；Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt and National Research Center for Applied Cybersecurity（德累斯顿技术大学计算机科学系及应用网络安全国家研究中心通用知识处理实验室）；ATHENE, Germany（德国ATHENE研究院）
Multimodal machine translation is one of the applications that integrates computer vision and language processing. It is a unique task given that in the field of machine translation, many state-of-the-arts algorithms still only employ textual information. In this work, we explore the effectiveness of reinforcement learning in multimodal machine translation. We present a novel algorithm based on the Advantage Actor-Critic (A2C) algorithm that specifically cater to the multimodal machine translation task of the EMNLP 2018 Third Conference on Machine Translation (WMT18). We experiment our propose…
University of Lincoln（林肯大学）；University of Toulouse III（图卢兹第三大学）
Training robots to perceive, act and communicate using multiple modalities still represents a challenging problem, particularly if robots are expected to learn efficiently from small sets of example interactions. We describe a learning approach as a step in this direction, where we teach a humanoid robot how to play the game of noughts and crosses. Given that multiple multimodal skills can be trained to play this game, we focus our attention to training the robot to perceive the game, and to interact in this game. Our multimodal deep reinforcement learning agent perceives multimodal features a…
IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage
The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六三研究所，南京）
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization
Guangdong University of Technology（广东工业大学）；Southern University of Science and Technology（南方科技大学）；Xi’an Jiaotong University（西安交通大学）；Guizhou Provincial Laboratory of Big Data, State Key Laboratory of Public Big Data, Guizhou University（贵州大学大数据省级重点实验室、公共大数据国家重点实验室）
For robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills through a trial and error method. This paper aims to develop a robot that gathers data during its interaction with a human and learns human interaction behaviour from the high-dimensional sensory information using end-to-end reinforcement learning. This paper demonstrates that the r…
The Chinese University of Hong Kong Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Maintaining the long-term exploration capability of the agent remains one of the critical challenges in deep reinforcement learning. A representative solution is to leverage reward shaping to provide intrinsic rewards for the agent to encourage exploration. However, most existing methods suffer from vanishing intrinsic rewards, which cannot provide sustainable exploration incentives. Moreover, they rely heavily on complex models and additional memory to record learning procedures, resulting in high computational complexity and low robustness. To tackle this problem, entropy-based methods are p…
Dual-Flow Reinforcement Learning with State-Aware Exploration
State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（智能绿色车辆与移动国家重点实验室，清华大学）；Tsinghua University-Toyota Joint Center（清华大学-丰田联合中心）；Tsinghua University–SAIC GM Wuling Joint Research Center（清华大学-上汽通用五菱联合研究中心）
MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning
Fudan University, Shanghai, China（复旦大学）；University of Science and Technology of China（中国科学技术大学）；Xi'an Jiaotong University, Xi'an, China（西安交通大学）；South China University of Technology, Guangzhou, China（华南理工大学）
With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words representations and average facial expression intensity, we develop a novel deep architecture for multimodal sentiment analysis that performs modality fusion at the word level. In this paper, we propose the Gated Multimodal Embedding LSTM with Temporal Attention (GME-LSTM(A)) model…
