inference-time-learning

该论文提出开放世界AI需要三项核心要求：推理时学习、丰富表示和预测性解纠缠，并在最大880亿参数的语言模型上验证了满足这些要求的模型能从相关任务数据中持续提升，而其他模型则会退化。

This paper argues that representing agent skills as code, rather than natural language, yields the best cost reduction for LLM agents, and introduces SpeedRunner, a coding agent that learns programmatic skills from past trajectories to improve performance while cutting costs across embodied environments.