Prime Intellect says NVIDIA used tasks validated on its verifiers, renderers, and prime-rl to train Nemotron 3.5 Super VL with GRPO. The post says enterprise agent failures can seed new verified tasks for further post-training and evaluation.
Part of a thread · earlier post
We validated tasks on verifiers, renderers, and prime-rl
NVIDIA used these verified tasks to train Nemotron 3.5 Super VL with GRPO
This offers a path to keep improving enterprise agents: use workflow failures to build the next set of verified tasks, then post-train and evaluate again
Source: Prime Intellect · x.comPublished · added here
