---
title: "Meta-Frieren: Beyond Single Level Online Learning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07169v1"
permalink: "https://feed.astralor.com/items/itm_c3e3decf6d00156152656ffb"
published: "2026-11-04T21:52:15.000Z"
score: 55
channel: "tech"
tags: ["AI Agent","Meta-Frieren","Beyond Single Level","Online Learning","Meta-Fri","Our","UCB-style"]
---

# Meta-Frieren: Beyond Single Level Online Learning

## At a glance

We study a two-stage online optimization problem: at each round, a meta-learner first selects an agent-environment pair, then the chosen agent interacts with the environment, and receives a reward. We introduce Meta-Fri…

## Key points

- We study a two-stage online optimization problem: at each round, a meta-learner first selects an agent-environment pair, then the chosen agent interacts with the environment, and receives a reward.
- We introduce Meta-Frieren, a general framework for maximizing cumulative reward in this setting.
- Our analysis yields a simple UCB-style criterion for meta-level selection and recovers prior guarantees as special cases while extending them to broader settings.

## Full text

We study a two-stage online optimization problem: at each round, a meta-learner first selects an agent-environment pair, then the chosen agent interacts with the environment, and receives a reward. We introduce Meta-Frieren, a general framework for maximizing cumulative reward in this setting. Our analysis yields a simple UCB-style criterion for meta-level selection and recovers prior guarantees as special cases while extending them to broader settings. We instantiate Meta-Frieren with GP-UCB under Bayesian and frequentist assumptions. We also derive, to our knowledge, the first high-probability regret bound for Feel-Good Thompson Sampling, specialize it to finite and parametric function classes, and integrate it into Meta-Frieren. Experiments support our theoretical results and demonstrate that Meta-Frieren can be successfully applied to hyperparameter optimization across multiple model classes.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_c3e3decf6d00156152656ffb