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

> Толық мәтін ағылшын тілінде

**Published:** 2026 ж. 26 қазан
**Author:** Ya Gao, Zhengtao Zou, Pekka Marttinen
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/kk/articles/beyond-on-policy-vs-off-policy-at-what-level-should-llm-agent-distillati

arXiv:2610.31918v1 Announce Type: new Abstract: Distilling interactive LLM agents requires choosing between teacher-generated demonstrations and student-generated experience, corresponding broadly to off-policy and on-policy distillation. While both have proven effective, we…

> Материал бастапқы дереккөзден алынған: **arXiv — cs.AI**
> [Толық мәтінді arXiv — cs.AI сайтында оқу](https://arxiv.org/abs/2610.31918)

**Тегтер:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*