EvoX: Meta-Evolution for Automated Discovery

TL;DR

EvoX is an adaptive evolutionary framework that jointly optimizes candidate solutions and search strategies, enabling dynamic adaptation during the search process, which leads to superior performance across diverse real-world tasks.

Contribution

EvoX introduces a novel method that co-evolves solutions and search strategies, allowing dynamic adaptation and improved optimization performance over existing fixed-strategy approaches.

Findings

EvoX outperforms existing methods on most of nearly 200 real-world tasks.

EvoX effectively adapts its search strategies during optimization.

EvoX demonstrates superior flexibility and efficiency in diverse problem domains.

Abstract

Recent work such as AlphaEvolve has shown that combining LLM-driven optimization with evolutionary search can effectively improve programs, prompts, and algorithms across domains. In this paradigm, previously evaluated solutions are reused to guide the model toward new candidate solutions. Crucially, the effectiveness of this evolution process depends on the search strategy: how prior solutions are selected and varied to generate new candidates. However, most existing methods rely on fixed search strategies with predefined knobs (e.g., explore-exploit ratios) that remain static throughout execution. While effective in some settings, these approaches often fail to adapt across tasks, or even within the same task as the search space changes over time. We introduce EvoX, an adaptive evolution method that optimizes its own evolution process. EvoX jointly evolves candidate solutions and the search strategies used to generate them, continuously updating how prior solutions are selected and varied based on progress. This enables the system to dynamically shift between different search strategies during the optimization process. Across nearly 200 real-world optimization tasks, EvoX outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.