From RL to IRL — Gaurav Mishra, Amazon AGI Lab

An 18-minute researcher talk on why coding agents that ace RL benchmarks fail when deployed: real environments have session expiry, irreversible actions, adversarial content, and ambiguous success criteria that the training setup never modeled. The taxonomy of failure modes and the harness-guardrail checklist are directly usable if you're deploying computer-use or coding agents today.

• Real failures are mundane and dangerous: agents guessing passwords when sessions expire, clicking sponsored ads instead of buttons, filling personal details on the wrong site.
• Six deployment gaps break RL assumptions: partial observability, irreversible actions, non-determinism, session expiration, ambiguous success, and adversarial content.
• Process reward models should penalize dangerous actions along the trajectory, not just score final outcomes; calibrated confidence tells the agent when to escalate.
• Practical loop: deploy early behind strong harness guardrails, collect real failure modes, retrain on those patterns, then gradually thin the harness.

Part of Issue Nº 005: How Unify cut agent costs 95%, and why RL-trained agents break in the wild