Search papers, labs, and topics across Lattice.
2
3
4
4
CrEST redefines credit assignment in RL by shifting the teacher's role from directing updates to modulating their magnitude, leading to substantial performance improvements in multi-turn agent training.
Forget synthetic data and overfitting: Environment Tuning lets LLM agents learn complex tool-use behaviors directly from the environment, slashing data needs and boosting generalization.