CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration

Complex image creation and editing often require more than a single generation or editing model. A user request may involve synthesizing images, localizing objects, segmenting regions, editing selected content, compositing intermediate assets, reading text, and enhancing the final result. Such tasks shift multimodal agents from perception-augmented reasoning to manipulation-centered visual creation, where tools must actively transform visual states rather than merely inspect them. However, existing multimodal tool-use agents are mostly optimized for perception, search, or domain-specific editing, and lack large-scale supervision for executable image-creation trajectories. In this paper, we introduce CanvasCraft, a large-scale multimodal tool-use dataset for complex image creation and editing, and \textbf{CanvasAgent}, a tool-augmented multimodal agent that learns to orchestrate heterogeneous visual tools through multi-turn interaction. CanvasCraft contains 140K fully annotated executable trajectories and 10K RL task specifications. CanvasAgent is first trained with SFT to learn executable reasoning-action trajectories, and is then optimized with GRPO using a hybrid reward that combines outcome- and process-level signals. During rollout, CanvasAgent inspects intermediate results, tracks visual assets, and adapts tool decisions to the evolving visual state. Experiments evaluate both final image quality and trajectory behavior, demonstrating the effectiveness of CanvasAgent and the proposed dataset for complex multi-tool image creation workflows.

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs

Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-computer interaction, where understanding human emotions is essential. However, existing benchmarks mainly formulate emotion understanding as a static recognition problem, leaving it largely unclear whether current MLLMs can understand emotion as a dynamic process that evolves, shifts between states, and unfolds across diverse social contexts. To bridge this gap, we present EmoTrans, a benchmark for evaluating emotion dynamics understanding in multimodal videos. EmoTrans contains 1,000 carefully collected and manually annotated video clips, covering 12 real-world scenarios, and further provides over 3,000 task-specific question-answer (QA) pairs for fine-grained evaluation. The benchmark introduces four tasks, namely Emotion Change Detection (ECD), Emotion State Identification (ESI), Emotion Transition Reasoning (ETR), and Next Emotion Prediction (NEP), forming a progressive evaluation framework from coarse-grained detection to deeper reasoning and prediction. We conduct a comprehensive evaluation of 18 state-of-the-art MLLMs on EmoTrans and obtain two main findings. First, although current MLLMs show relatively stronger performance on coarse-grained emotion change detection, they still struggle with fine-grained emotion dynamics modeling. Second, socially complex settings, especially multi-person scenarios, remain substantially challenging, while reasoning-oriented variants do not consistently yield clear improvements. To facilitate future research, we publicly release the benchmark, evaluation protocol, and code at https://github.com/Emo-gml/EmoTrans.

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group Relative Policy Optimization (GRPO) eliminates the need for critic models but suffers from indiscriminate credit assignment for intermediate steps, which limits its ability to identify effective reasoning strategies and incurs overthinking. In this work, we introduce a model-free and verifiable process supervision via probing the model's belief in the correct answer throughout its reasoning trajectory. By segmenting the generation into discrete steps and tracking the conditional probability of the correct answer appended at each segment boundary, we efficiently compute interpretable segment-wise progress measurements to refine GRPO's trajectory-level feedback. This approach enables more targeted and sample-efficient policy updates, while avoiding the need for intermediate supervision derived from costly Monte Carlo rollouts or auxiliary models. Experiments on mathematical and general-domain benchmarks show consistent gains over GRPO across diverse models: up to 2.6-point accuracy improvements and 13.7% reasoning-length reductions on math tasks, and up to 2.4 points and 4% on general-domain tasks, demonstrating strong generalization.

OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models

Multimodal large language models (MLLMs) have achieved remarkable performance across a wide range of vision language tasks. However, their ability in low-level visual perception, particularly in detecting fine-grained visual discrepancies, remains underexplored and lacks systematic analysis. In this work, we introduce OddGridBench, a controllable benchmark for evaluating the visual discrepancy sensitivity of MLLMs. OddGridBench comprises over 1,400 grid-based images, where a single element differs from all others by one or multiple visual attributes such as color, size, rotation, or position. Experiments reveal that all evaluated MLLMs, including open-source families such as Qwen3-VL and InternVL3.5, and proprietary systems like Gemini-2.5-Pro and GPT-5, perform far below human levels in visual discrepancy detection. We further propose OddGrid-GRPO, a reinforcement learning framework that integrates curriculum learning and distance-aware reward. By progressively controlling the difficulty of training samples and incorporating spatial proximity constraints into the reward design, OddGrid-GRPO significantly enhances the model's fine-grained visual discrimination ability. We hope OddGridBench and OddGrid-GRPO will lay the groundwork for advancing perceptual grounding and visual discrepancy sensitivity in multimodal intelligence. Code and dataset are available at https://wwwtttjjj.github.io/OddGridBench/.

BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI Agents

GUI agents are designed to automate repetitive tasks and enhance productivity. However, existing GUI agents struggle to recover once they follow an incorrect exploration path, often leading to task failure. In this work, we model GUI task execution as a DFS process and propose BEAP-Agent, a DFS-based framework that supports long-range, multi-level state backtracking with dynamic task tracking and updating. The framework consists of three collaborative components: Planner, Executor, and Tracker. Together, they enable effective task exploration and execution. BEAP-Agent fills the gap in systematic backtracking mechanisms for GUI agents, offering a systematic solution for long-horizon task exploration. We conducted a systematic evaluation on the OSWorld benchmark, where BEAP-Agent achieved an accuracy of 28.2%, validating the effectiveness of the proposed method.

LlamaSeg: Image Segmentation via Autoregressive Mask Generation

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens and employing a LLaMA-style Transformer to predict them directly from image inputs. By adhering to the next-token prediction paradigm, our approach naturally integrates segmentation tasks into autoregressive architectures. To support large-scale training, we introduce a data annotation pipeline and construct the SA-OVRS dataset, which contains 2M segmentation masks annotated with over 5,800 open-vocabulary labels or diverse textual descriptions, covering a wide spectrum of real-world scenarios. This enables our model to localize objects in images based on text prompts and to generate fine-grained masks. To more accurately evaluate the quality of masks produced by visual generative models, we further propose a composite metric that combines Intersection over Union (IoU) with Average Hausdorff Distance (AHD), offering a more precise assessment of contour fidelity. Experimental results demonstrate that our method surpasses existing generative models across multiple datasets and yields more detailed segmentation masks.

VisNumBench: Evaluating Number Sense of Multimodal Large Language Models

Can Multimodal Large Language Models (MLLMs) develop an intuitive number sense similar to humans? Targeting this problem, we introduce Visual Number Benchmark (VisNumBench) to evaluate the number sense abilities of MLLMs across a wide range of visual numerical tasks. VisNumBench consists of about 1,900 multiple-choice question-answer pairs derived from both synthetic and real-world visual data, covering seven visual numerical attributes and four types of visual numerical estimation tasks. Our experiments on VisNumBench led to the following key findings: (i) The 17 MLLMs we tested, including open-source models such as Qwen2.5-VL and InternVL2.5, as well as proprietary models like GPT-4o and Gemini 2.0 Flash, perform significantly below human levels in number sense-related tasks. (ii) Multimodal mathematical models and multimodal chain-of-thought (CoT) models did not exhibit significant improvements in number sense abilities. (iii) Stronger MLLMs with larger parameter sizes and broader general abilities demonstrate modest gains in number sense abilities. We believe VisNumBench will serve as a valuable resource for the research community, encouraging further advancements in enhancing MLLMs' number sense abilities. All benchmark resources, including code and datasets, will be publicly available at https://wwwtttjjj.github.io/VisNumBench/.

Accurate Segmentation of Optic Disc And Cup from Multiple Pseudo-labels by Noise-Aware Learning

Optic disc and cup segmentation play a crucial role in automating the screening and diagnosis of optic glaucoma. While data-driven convolutional neural networks (CNNs) show promise in this area, the inherent ambiguity of segmenting object and background boundaries in the task of optic disc and cup segmentation leads to noisy annotations that impact model performance. To address this, we propose an innovative label-denoising method of Multiple Pseudo-labels Noise-aware Network (MPNN) for accurate optic disc and cup segmentation. Specifically, the Multiple Pseudo-labels Generation and Guided Denoising (MPGGD) module generates pseudo-labels by multiple different initialization networks trained on true labels, and the pixel-level consensus information extracted from these pseudo-labels guides to differentiate clean pixels from noisy pixels. The training framework of the MPNN is constructed by a teacher-student architecture to learn segmentation from clean pixels and noisy pixels. Particularly, such a framework adeptly leverages (i) reliable and fundamental insights from clean pixels and (ii) the supplementary knowledge within noisy pixels via multiple perturbation-based unsupervised consistency. Compared to other label-denoising methods, comprehensive experimental results on the RIGA dataset demonstrate our method's excellent performance and significant denoising ability.

PMP-Swin: Multi-Scale Patch Message Passing Swin Transformer for Retinal Disease Classification

Retinal disease is one of the primary causes of visual impairment, and early diagnosis is essential for preventing further deterioration. Nowadays, many works have explored Transformers for diagnosing diseases due to their strong visual representation capabilities. However, retinal diseases exhibit milder forms and often present with overlapping signs, which pose great difficulties for accurate multi-class classification. Therefore, we propose a new framework named Multi-Scale Patch Message Passing Swin Transformer for multi-class retinal disease classification. Specifically, we design a Patch Message Passing (PMP) module based on the Message Passing mechanism to establish global interaction for pathological semantic features and to exploit the subtle differences further between different diseases. Moreover, considering the various scale of pathological features we integrate multiple PMP modules for different patch sizes. For evaluation, we have constructed a new dataset, named OPTOS dataset, consisting of 1,033 high-resolution fundus images photographed by Optos camera and conducted comprehensive experiments to validate the efficacy of our proposed method. And the results on both the public dataset and our dataset demonstrate that our method achieves remarkable performance compared to state-of-the-art methods.

MSE-Nets: Multi-annotated Semi-supervised Ensemble Networks for Improving Segmentation of Medical Image with Ambiguous Boundaries

Medical image segmentation annotations exhibit variations among experts due to the ambiguous boundaries of segmented objects and backgrounds in medical images. Although using multiple annotations for each image in the fully-supervised has been extensively studied for training deep models, obtaining a large amount of multi-annotated data is challenging due to the substantial time and manpower costs required for segmentation annotations, resulting in most images lacking any annotations. To address this, we propose Multi-annotated Semi-supervised Ensemble Networks (MSE-Nets) for learning segmentation from limited multi-annotated and abundant unannotated data. Specifically, we introduce the Network Pairwise Consistency Enhancement (NPCE) module and Multi-Network Pseudo Supervised (MNPS) module to enhance MSE-Nets for the segmentation task by considering two major factors: (1) to optimize the utilization of all accessible multi-annotated data, the NPCE separates (dis)agreement annotations of multi-annotated data at the pixel level and handles agreement and disagreement annotations in different ways, (2) to mitigate the introduction of imprecise pseudo-labels, the MNPS extends the training data by leveraging consistent pseudo-labels from unannotated data. Finally, we improve confidence calibration by averaging the predictions of base networks. Experiments on the ISIC dataset show that we reduced the demand for multi-annotated data by 97.75\% and narrowed the gap with the best fully-supervised baseline to just a Jaccard index of 4\%. Furthermore, compared to other semi-supervised methods that rely only on a single annotation or a combined fusion approach, the comprehensive experimental results on ISIC and RIGA datasets demonstrate the superior performance of our proposed method in medical image segmentation with ambiguous boundaries.