# Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL

> Полный текст доступен на английском

**Published:** 9 октября 2026 г.
**Author:** Hanyu Wang, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Makoto Fukushima, Jinghui Chen, Vaishnav Tadiparthi
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/balancing-reference-guidance-and-free-generation-in-trajectory-rollouts

A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model in generating a trajectory of its own. How much reference guidance should we provide? We study this question through prefix…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2610.11128)

**Теги:** #arXiv

---

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