Search papers, labs, and topics across Lattice.
3
0
6
10
Harness-native agents trained with OpenForgeRL outperform larger models on complex tasks, revealing that some harnesses are significantly harder to learn than others.
AHR achieves state-of-the-art performance in text classification with a fraction of the parameters, revolutionizing how LLMs can adapt to limited data.
Forget toy tasks: scaling synthetic computer environments unlocks surprisingly effective training data for agents tackling month-long, real-world productivity workflows.
