בניית אימון סגור לסוכנות רב-מודאלית בקנה מידה

תקציר מקורי באנגליתThis talk covers how Uber designed evals for its food enhancement agent, which edits food photography to better present dishes for smaller, independent Uber Eats merchants, along with the pitfalls and lessons learned along the way. The problem is uniquely hard: the system must stay faithful to the original dish, preserve each merchant's brand and packaging, and avoid homogenizing the marketplace, all without an existing playbook for multimodal evals in a narrow domain. Soumya Gupta and Jai Chopra explain how they navigated reward hacking, built a closed feedback loop combining offline and online signals, and balanced creativity against rigid safety guardrails at scale. ML and applied AI practitioners working on multimodal systems, agentic pipelines, or eval design will take away practical