ECHO: Terminal Agents Learn World Models for Free 事件

ECHO: Terminal Agents Learn World Models for Free arXiv:2605.24517v1 Announce Type: cross Abstract: CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream -- stdout, errors, files, logs, and traces -- records the consequences. We argue that this stream is a supervision signal, but standard agent RL discards it: GRPO-style training updates action tokens with sparse outcome-level rewards while ign