# OBC-Prune: Outcome-Based Calibration for Large Reasoning Model Pruning

> Заголовок на английском

> Полный текст доступен на английском

**Published:** 17 сентября 2026 г.
**Author:** Ha Lan Nguyen, Huy Hoang Tran, Trac-Duy Tran, Dung D. Le
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/obc-prune-outcome-based-calibration-for-large-reasoning-model-pruning

Large reasoning models (LRMs) generate long chain-of-thought traces before answering, creating significant inference overhead. Pruning can reduce this cost, but its effectiveness depends on the calibration data used to estimate parameter importance. Recent work calibrates on the…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2609.17890)

**Теги:** #arXiv

---

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