The paper proposes HADA, a dual-agent framework that automates the design of Meta-Black-Box Optimization (MetaBBO) algorithms. A task agent evolves the algorithm's codebase, while a hyper agent modifies the task agent and itself for open-ended self-improvement. Starting from a naive template, HADA discovers novel MetaBBO variants that surpass human-designed baselines. The approach achieves 121.7%, 114.7%, and 104.3% performance improvements on single-objective, constrained, and multi-objective optimization problems respectively. This is interesting because it is the first fully automated system for designing complex learning-assisted optimizers, reducing human subjectivity and enabling fast adaptation across domains.
Self-modifying coding agents evolve learned optimizers from simple templates
The authors demonstrate a dual-agent system that iteratively rewrites both an optimization codebase and the agents directing its development.
Academic
Zipei Yu · Yue-Jiao Gong · Zeyuan Ma · Yuncheng Jiang · Zhiguang Cao
South China University of Technology · South China Normal University · Singapore Management Univeristy
Research Digest··2 min read
In one line
HADA automates MetaBBO algorithm design using recursive self-improvement, outperforming human-designed baselines significantly.
Before you read this
Three ideas this paper builds onrecursive self-improvementAn AI system repeatedly uses its own outputs to enhance its capabilities, creating a feedback loop for autonomous improvement.66 papers →coding agentAn AI-powered software system that autonomously writes, modifies, or extends source code based on high-level instructions.167 papers →self-evolving agentAn agent that improves by reusing its own experience, memory, or self-generated feedback, with success depending on verification and design.96 papers →
Read it as
Yu et al. present HADA, a framework that treats the design of learnable black-box optimizers as a coding task.
The authors built a dual-agent framework for Meta-Black-Box Optimization, or MetaBBO, in which a learned policy controls design choices for a lower-level optimizer.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.