Search papers, labs, and topics across Lattice.
5
0
7
Rather than treating agent trajectories as dead post-training demonstrations, researchers can now resurrect thousands of fully executable, verifiable terminal environments directly from tool-execution logs.
Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.
Forget hand-crafted benchmarks: CUA-Gym's auto-generated training data lets computer-use agents crush existing open-source models on real-world tasks.
LLM benchmark accuracy jumps 10% when evaluated on a cleaned-up version of Humanity's Last Exam, highlighting the significant impact of dataset noise on performance metrics.
