• Agents will inhabit streams of experience, rather than short snippets of interaction. • Their actions and observations will be richly grounded in the environment, rather than interacting via human dialogue alone. • Their rewards will be grounded in their experience of the environment, rather than coming from human prejudgement.
In the era ofhuman data, language-based AI has largely focused on short interaction episodes: e.g., a user asks a question and (perhaps after a few thinking steps or tool-use actions) the agent responds. Typically, little or no information carries over from one episode to the next, precluding any adaptation over time.
