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 mode...

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 a fresh model session, and durable information is reintroduced on…

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 a fresh model session, and durable information is reintroduced only through explicit interfaces such as persistent memory files, reports, and repository state. Within a round, an orchestrator explores, plans and builds many alternative approaches with specialized agents, while a task-grounded verifier verifies the work and supplies an objective reward for measuring progress. This reward is distilled back into the persistent state, which updates the effective policy for the next round. In this technical report, we formalize this loop and describe its persistent state and verification interfaces. We then demonstrate its use in three domains, namely olympiad mathematics, data science, and cybersecurity. On the six fresh problems of the 2026 International Math

AutoFyn is a powerful agent using that adapts a frozen model across many rounds by updating persistent state from verified reward signals rather than model

A new technical report introduces AutoFyn, an agent harness that improves a frozen model's long-horizon performance by updating persistent memory and reports from verified rewards instead of retraining weights.

Abstract page for arXiv paper 2609.05446: AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents