… In parallel, EditReward-Compass contains 2,251 preference pairs that simulate realistic reward modeling scenarios during RL optimization. AI-generated summary Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. …
… The following papers were recommended by the Semantic Scholar API Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models 2026 ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation 2026 $M^2$-VLA: Boosting Vision-Language Models for… …
… AI-generated summary Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. …
… Across 13 proprietary and open-source LLM agents, the best-performing model achieves only 46% success rate pass@1 , while open-source models reach at most 19%, revealing a substantial gap between current agent capabilities and the demands of real-world clinical workflows. …
… AI-generated summary We introduce SeePhys Pro, a fine-grained modality transfer benchmark that studies whether models preserve the same reasoning capability when critical information is progressively transferred from text to image. …
… This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement. …
… We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single model, identifying capability loss in different ways: mixed RLVR suffers from inter-capability divergence cost, while the pipeline of first training experts and then performing OPD , tho… …
… Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following , and efficient deployment, especially in text-rich and compositionally complex scenarios. …
… AI-generated summary Instruction following is a fundamental capability of large language models LLMs , yet continuously improving this capability remains challenging. …
… To frame this shift, we introduce a five-level taxonomy: Atomic Generation, Conditional Generation, In-Context Generation, Agentic Generation, and World-Modeling Generation, progressing from passive renderers to interactive, agentic, world-aware generators. …