Prompt optimization increased the reward of a research agent by 0.079
On held-out topics, the reward went from 0.702 to 0.781, but a scalar reward gave a negative result.
Claimed, not confirmed
Sources
Posted
What matters in AI.
SubscribeOn held-out topics, the reward went from 0.702 to 0.781, but a scalar reward gave a negative result.
Claimed, not confirmed
Posted
