MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
MARGIN calibrates multi-model confidence at runtime and lifts answer-selection accuracy by up to 14 points.
1 stories, newest first · one card per story
MARGIN calibrates multi-model confidence at runtime and lifts answer-selection accuracy by up to 14 points.
Today 1.5K readers · 2.4K views · 768 reads · all time 189K views