# Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization

**Published:** October 12, 2026
**Author:** Jiaqi Tian, Ting Long
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/mitigating-capability-degradation-in-llm-self-improvement-via-representa

arXiv:2610.12855v1 Announce Type: new Abstract: On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the same model as both teacher and student under different conditioning contexts.…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.12855)

**Tags:** #arXiv

---

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