# AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents

**Published:** September 9, 2026
**Author:** Adib Hasan, Daniel Schaffield, Akashnil Dutta, Tarik Adnan Moon
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/autofyn-technical-report-non-parametric-expert-iteration-for-long-horizo

arXiv:2609.05446v1 Announce Type: new Abstract: We introduce AutoFyn, an agent harness inspired by the Expert Iteration algorithm, adapting a frozen model across many rounds by updating persistent state from verified reward signals rather than model weights. Each round begins…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.05446)

**Tags:** #arXiv

---

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