Dream2Discern predicts multi-agent failures from hard variants
It reports over 90% trajectory-level weighted accuracy on AFTraj-2K and StepShield without collecting new trajectories.
1 stories, newest first · one card per story
It reports over 90% trajectory-level weighted accuracy on AFTraj-2K and StepShield without collecting new trajectories.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views