Intern-Decision：基于自回归掩码语言建模的高效多模态决策

arXiv 2610.22131 · 20 人推荐 · 附代码 InternLM/Intern-Decision（786 stars）。Interactive agents repeatedly choose among a finite set of actions, labels, or ordinal outcomes. Generating a free-form response for each choice adds latency and complicates the interface between a model and its environment. We present Intern-Decision, a family of 0.8B, 2B, and 4B multimodal decision models that return structured choices and candidate probabilities from text and optional images. Our autoregressive masked language modeling objective places one decision placeholder per field in a