Jiantao Jiao and Meriem Boubdir from @nvidia present “Closing the Loop: From Agentic Evaluation at Scale to Actionable Model Insights”—using NeMo Gym and failure analysis to turn agent trajectories into insights for model development.
NVIDIA presents a method for turning agent evaluations into model insights
AINVIDIA researchers Jiantao Jiao and Meriem Boubdir present a method using NeMo Gym and failure analysis to turn agent trajectories into insights for model development. The talk, titled "Closing the Loop: From Agentic Evaluation at Scale to Actionable Model Insights," covers evaluating agents at scale.
Source details
LMSYS Org · x.comPublished · added here
Original title: Jiantao Jiao and Meriem Boubdir from @nvidia present “Closing the Loop: From Agentic Evaluation at Scale to Actionable Model Insights”—us...