零标签+代码驱动，用Litmus自动化定义AI评估指标，告别传统人工标注。
arXiv:2606.23403v1 Announce Type: new Abstract: As agentic LLM systems move from prototypes to deployment across increasingly diverse domains, evaluat…
代码驱动的智能体式图像生成新范式，用自然语言编程实现更可控、更灵活的AI绘图。
arXiv:2605.30248v1 Announce Type: new Abstract: Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents en…
重新定义物理推理评估：代码驱动视频重建让MLLMs必须真正理解物理规律，而非表面识别。
arXiv:2602.13294v3 Announce Type: replace Abstract: Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynami…
一篇探讨将代码作为智能体（Agent）驱动框架的前沿论文，为AI代理开发提供新思路与理论基础。
arXiv:2605.18747v1 Announce Type: new Abstract: Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generat…