Large-scale reinforcement learning with verifiable rewards (RLVR) has proven effective in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs often rely on external tools to assist in task-solving processes. However, current RL algorithms typically employ trajectory-level rollout sampling, consistently neglecting the fine-grained exploration of multi-turn tool-call steps. To bridge this gap, we propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents. Our preliminary experiments reveal that LLMs frequently exhibit increased uncertainty after tool-call steps, as evidenced by higher entropy in the distribution of generated tokens. Motivated by this, ARPO incorporates an entropy-based adaptive rollout mechanism, encouraging the policy model to adaptively branch sampling during high-entropy tool-call rounds, thereby promoting step-level exploration of latent tool-use behaviors. By integrating an advantage attribution estimation, ARPO enables LLMs to internalize advantage differences in stepwise tool-use interactions. Experiments across 13 challenging benchmarks demonstrate ARPO's superiority over trajectory-level RL algorithms. Remarkably, ARPO achieves improved performance using only half of the tool-use budget required by existing methods, offering a scalable solution for aligning LLM-based agents with real-time dynamic environments. Our codes are released at https://github.com/RUC-NLPIR/ARPO.
Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on improving the model structure and training data of MRMs, there has been limited exploration into the effectiveness of long-term reasoning capabilities for reward modeling and how to activate these capabilities in MRMs. In this paper, we explore how Reinforcement Learning (RL) can be used to improve reward modeling. Specifically, we reformulate the reward modeling problem as a rule-based RL task. However, we observe that directly applying existing RL algorithms, such as Reinforce++, to reward modeling often leads to training instability or even collapse due to the inherent limitations of these algorithms. To address this issue, we propose the StableReinforce algorithm, which refines the training loss, advantage estimation strategy, and reward design of existing RL methods. These refinements result in more stable training dynamics and superior performance. To facilitate MRM training, we collect 200K preference data from diverse datasets. Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks. Compared to previous SOTA models, R1-Reward achieves a 8.4% improvement on the VL Reward-Bench and a 14.3% improvement on the Multimodal Reward Bench. Moreover, with more inference compute, R1-Reward's performance is further enhanced, highlighting the potential of RL algorithms in optimizing MRMs.
Recent advances in text-to-video generation have sparked interest in generative video editing tasks. Previous methods often rely on task-specific architectures (e.g., additional adapter modules) or dedicated customizations (e.g., DDIM inversion), which limit the integration of versatile editing conditions and the unification of various editing tasks. In this paper, we introduce UNified In-Context Video Editing (UNIC), a simple yet effective framework that unifies diverse video editing tasks within a single model in an in-context manner. To achieve this unification, we represent the inputs of various video editing tasks as three types of tokens: the source video tokens, the noisy video latent, and the multi-modal conditioning tokens that vary according to the specific editing task. Based on this formulation, our key insight is to integrate these three types into a single consecutive token sequence and jointly model them using the native attention operations of DiT, thereby eliminating the need for task-specific adapter designs. Nevertheless, direct task unification under this framework is challenging, leading to severe token collisions and task confusion due to the varying video lengths and diverse condition modalities across tasks. To address these, we introduce task-aware RoPE to facilitate consistent temporal positional encoding, and condition bias that enables the model to clearly differentiate different editing tasks. This allows our approach to adaptively perform different video editing tasks by referring the source video and varying condition tokens "in context", and support flexible task composition. To validate our method, we construct a unified video editing benchmark containing six representative video editing tasks. Results demonstrate that our unified approach achieves comparable performance with task specialists and exhibits emergent task composition abilities.
Unsigned distance functions (UDFs) have been a vital representation for open surfaces. With different differentiable renderers, current methods are able to train neural networks to infer a UDF by minimizing the rendering errors with the UDF to the multi-view ground truth. However, these differentiable renderers are mainly handcrafted, which makes them either biased on ray-surface intersections, or sensitive to unsigned distance outliers, or not scalable to large scenes. To resolve these issues, we present a novel differentiable renderer to infer UDFs more accurately. Instead of using handcrafted equations, our differentiable renderer is a neural network which is pre-trained in a data-driven manner. It learns how to render unsigned distances into depth images, leading to a prior knowledge, dubbed volume rendering priors. To infer a UDF for an unseen scene from multiple RGB images, we generalize the learned volume rendering priors to map inferred unsigned distances in alpha blending for RGB image rendering. To reduce the bias of sampling in UDF inference, we utilize an auxiliary point sampling prior as an indicator of ray-surface intersection, and propose novel schemes towards more accurate and uniform sampling near the zero-level sets. We also propose a new strategy that leverages our pretrained volume rendering prior to serve as a general surface refiner, which can be integrated with various Gaussian reconstruction methods to optimize the Gaussian distributions and refine geometric details. Our results show that the learned volume rendering prior is unbiased, robust, scalable, 3D aware, and more importantly, easy to learn. Further experiments show that the volume rendering prior is also a general strategy to enhance other neural implicit representations such as signed distance function and occupancy. We evaluate our method on both widely used benchmarks and real scenes, and report superior performance over the state-of-the-art methods.
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on importance-ratio clipping to constrain overconfident positive and negative gradients. However, in practice, we observe a systematic shift in the importance-ratio distribution—its mean falls below 1 and its variance differs substantially across timesteps. This left-shifted and inconsistent distribution prevents positive-advantage samples from entering the clipped region, causing the mechanism to fail in constraining overconfident positive updates. As a result, the policy model inevitably enters an implicit over-optimization stage —while the proxy reward continues to increase, essential metrics such as image quality and text–prompt alignment deteriorate sharply, ultimately making the learned policy impractical for real-world use. To address this issue, we introduce GRPO-Guard , a simple yet effective enhancement to existing GRPO frameworks. Our method incorporates ratio normalization, which restores a balanced and step-consistent importance ratio, ensuring that PPO clipping properly constrains harmful updates across denoising timesteps. In addition, a gradient reweighting strategy equalizes policy gradients over noise conditions, preventing excessive updates from particular timestep regions. Together, these designs act as a regulated clipping mechanism, stabilizing optimization and substantially mitigating implicit over-optimization without relying on heavy KL regularization. Extensive experiments on multiple diffusion backbones (e.g., SD3.5M, Flux.1-dev) and diverse proxy tasks demonstrate that GRPO-Guard significantly reduces over-optimization while maintaining or even improving generation quality. We provide detailed demonstrations of the over-optimization process and corresponding visualizations in Supplementary Materials. 5 .
