Abstract
In this work, we argue that large language models (LLMs), though trained to predict only the next token, exhibit emergent planning behaviors: . Through simple probing, we demonstrate that LLM prompt representations encode global attributes of their entire responses, including (e.g., response length, reasoning steps), (e.g., character choices in storywriting, multiple-choice answers at the end of response), and (e.g., answer confidence, factual consistency). In addition to identifying response planning, we explore how it scales with model size across tasks and how it evolves during generation. The findings that LLMs plan ahead for the future in their hidden representations suggest potential applications for improving transparency and generation control.