From RL to IRL — Gaurav Mishra, Amazon AGI Lab
- Source
- AI Engineer
- Author
- AI Engineer
- Date
- 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.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Reframes reliability as training for recovery rather than thickening the around the model.
“Asked to file an expense, the agent gets signed out mid task, reasons that it can infer the password, guesses twice, and locks the account.”
AI Engineer
“Both are real trajectories from early browser training runs at the Amazon AGI Lab, and Gaurav Mishra's summary is that RL worked while the world was a game, and IRL starts when the game fights back.”
AI Engineer
“Observability is partial, since the DOM misses content baked into images and the screenshot misses whatever needs scrolling. Actions are irreversible, credentials expire mid trajectory, and done routinely does not mean successful.”
AI Engineer
“Sandboxes train on layout shift, slow loads, pop ups, focus stealing, and stale tabs, and recovery becomes a native model action instead of an infra reset, so the agent refreshes, backtracks, waits, or escalates.”
AI Engineer
“A process reward model penalizes dangerous steps along the path instead of scoring only the outcome, and calibrated confidence teaches the agent to weigh whether an action is authorized, reversible, and visible before committing.”
AI Engineer
Checking sign-in…
Loading comments…