Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
5
Chasing large token-level teacher-student gaps in agent distillation is largely misguided: local divergence fails to predict task completion, whereas unpenalized minor deviations often trigger catastrophic multi-turn failure.
Achieving high-quality model performance with just 10% of the required labels could revolutionize the scalability of RLVR in large language models.