Alvin Zhang

@zalvin39105

JHU Undergraduate Junior | currently interested in: reasoning, memory, continue learning, and reinforcement learning | applying p.h.d this cycle | I play chess

following
followers

Models trained with Harness Learning are claimed to nearly double performance on challenging unseen tasks

A post describes training a model to revise agent harnesses using execution feedback. It says the model can then improve harnesses for unseen tasks while its weights stay fixed at test time.

5 Sources, 20d ago, updated 20d ago

Featured in

Models trained with Harness Learning are claimed to nearly double performance on challenging unseen tasks

Featured in

Models trained with Harness Learning are claimed to nearly double performance on challenging unseen tasks