Search papers, labs, and topics across Lattice.
4
0
7
0
Decoupling task synthesis from on-policy rollouts solves the learning-signal saturation bottleneck in terminal agents, boosting long-horizon RL performance by up to 18 percentage points on Terminal-Bench 2.1.
SkillSynth's skill graph approach lets you explicitly control the diversity of execution trajectories during terminal task synthesis, leading to more effective agent training.
A single graph foundation model can now achieve state-of-the-art anomaly detection across diverse graph domains, thanks to a new theory of "Anomaly Disassortativity" that tackles domain shift.
Graph-based code representations, largely unexplored in automated patch correctness assessment, crush sequence- and heuristic-based methods, achieving 82.6% accuracy in predicting patch correctness.
