Author

Ya Gao

h-index 1 View on Semantic Scholar

We have 1 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?

It is found that student-induced histories paired with teacher-generated action prefixes generally provide the strongest standalone training signal, whereas following the student at both levels generally performs worst, and fully on-policy data becomes beneficial when incorporated into a mixture with other configuratio...

Ya Gao, Zheng-Tao Zou, Pekka Marttinen · 0 citations