single mention · inference & serving
GPT-4 high-level policy
GPT-4 is used as the high-level policy for evaluating or selecting subtasks.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See agentic scaffolding for the methods filed beside it.
Also called use GPT-4 as the high-level policy.
Filed under inference & serving › agentic scaffolding