Search papers, labs, and topics across Lattice.
2
0
5
6
AI agents can learn to climb leaderboards in complex adversarial games by refining executable policies, but struggle with intricate rule sets
Frontis-MA1 achieves a remarkable 71.21% Medal Average on MLE-Bench Lite, outperforming leading models and showcasing the potential of AI systems to recursively improve their own engineering processes.
