---
title: "Reinforced In-Context Black-Box Optimization"
authors:
  - "Lei Song"
  - "Chen-Xiao Gao"
  - "Ke Xue"
  - "Chenyang Wu"
  - "Dong Li"
  - "Jianye Hao"
  - "Zongzhang Zhang"
  - "Chao Qian"
doi: "10.24963/ijcai.2025/994"
url: "https://ijcai.org/proceedings/2025/994"
pdf: "https://ijcai.org/proceedings/2025/0994.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "8939-8947"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Evolutionary learning"
  - "Search: S: Search and machine learning"
  - "Search: S: Evolutionary computation"
---

# Reinforced In-Context Black-Box Optimization

Lei Song, Chen-Xiao Gao, Ke Xue, Chenyang Wu, Dong Li, Jianye Hao, Zongzhang Zhang, Chao Qian

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 8939-8947. DOI: [10.24963/ijcai.2025/994](https://doi.org/10.24963/ijcai.2025/994)

## Abstract

Black-Box Optimization (BBO) has found successful applications in many fields of science and engineering. Recently, there has been a growing interest in meta-learning particular components of BBO algorithms to speed up optimization and get rid of tedious hand-crafted heuristics. As an extension, learning the entire algorithm from data requires the least labor from experts and can provide the most flexibility. In this paper, we propose RIBBO, a method to reinforce-learn a BBO algorithm from offline data in an end-to-end fashion. RIBBO employs expressive sequence models to learn the optimization histories produced by multiple behavior algorithms and tasks, leveraging the in-context learning ability of large models to extract task information and make decisions accordingly. Central to our method is to augment the optimization histories with regret-to-go tokens, which are designed to represent the performance of an algorithm based on cumulative regret over the future part of the histories. The integration of regret-to-go tokens enables RIBBO to automatically generate sequences of query points that are positively correlated to the user-desired regret, verified by its universally good empirical performance on diverse problems, including BBO benchmark, hyper-parameter optimization, and robot control problems.