…models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step…
…Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary…
…This design has two limitations: it covers only a narrow subset of everyday visual stress es, and some perturbations rarely appear in realistic embodied scenes. This gap raises a fundamental question: how…
…Jiaqi Tang , , , , , , , , Abstract Robust-U1 enhances multimodal large language models' robustness against visual corruptions through self-recovery capabilities that improve both visual quality and reasoning performance. Generated by Qwen/Qwen2.5-Coder…
…play training with static-difficulty instructions that cannot evolve as the model's capabilities improve. To address these limitations, we propose SEIF (Self-Evolving Reinforcement Learning for Instruction Following), a self-evolving…
…Cheng Qian , , Jiayu Liu , , , , , , , , , , Abstract Large language models demonstrate limited creative problem-solving abilities when required to repurpose objects based on affordance reasoning, indicating a gap in current AI capabilities for novel…
…Kirscher , , , , , , , , , , , , , , , , , Abstract Researchers developed a new dataset and challenge for pancreatic cancer staging that emphasizes uncertainty-aware AI models capable of handling ambiguous tumor-vessel interfaces, revealing that traditional segmentation metrics fail…
…Jingwen Chen , Wenkai Yang , , , , , , , , Abstract Experience internalization enables continual learning in large language models by converting past interactions into reusable capabilities, with key findings on experience granularity, injection patterns, and internalization regimes…
…Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities . To address this, we propose iWorld-Bench , a comprehensive benchmark for training and testing world…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Personalization is a crucial capability of modern language agents . However, current research primarily positions personalized agents as passive responders to user preferences, limiting their…