pretty interesting, this new NVIDIA framework represents agents as python objects, so the actions the agent can take are functions, fields are agent states, prompts are docstrings, and deterministic code it can run, alongside non deterministic "..." that the agent will write some code to solve and give you back a return value for
I'm really curious how well this works in practice and if any big models end up getting RL'ed / fine tuned with this harness
going to try it myself tomorrow and see
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
A distinct approach to AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → authoring that collapses prompt, state and code into ordinary Python structure.
