SERA trains recursive agents to score their own subtasks
On two text benchmarks, SERA beat recursive-agent baselines by 5.38 and 13.14 points on average.
1 stories, newest first · one card per story
On two text benchmarks, SERA beat recursive-agent baselines by 5.38 and 13.14 points on average.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views