Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EvoX: Meta-Evolution for Automated Discovery

Shu Liu, Shubham Agarwal, Monishwaran Maheswaran, Mert Cemri, Zhifei Li, Qiuyang Mang, Ashwin Naren, Ethan Boneh, Audrey Cheng, Melissa Z. Pan, Alexander Du, Kurt Keutzer, Alexandros G. Dimakis, Koushik Sen, Matei Zaharia, Ion Stoica

TL;DR

EvoX is introduced, an adaptive evolution method that optimizes its own evolution process, and outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.

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.

EvoX: Meta-Evolution for Automated Discovery

TL;DR

EvoX is introduced, an adaptive evolution method that optimizes its own evolution process, and outperforms existing AI-driven evolutionary methods including AlphaEvolve, OpenEvolve, GEPA, and ShinkaEvolve on the majority of tasks.

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.
Paper Structure (41 sections, 9 equations, 4 figures, 12 tables, 1 algorithm)

This paper contains 41 sections, 9 equations, 4 figures, 12 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Contributions.
  3. Related Work
  4. Context and Memory Management.
  5. LLM-Guided Evolutionary Search.
  6. Meta-Learning and Learning to Optimize.
  7. EvoX: Meta-Evolving the Search Strategy.
  8. Problem Formulation
  9. Candidate solution evaluation.
  10. Solution population database.
  11. Search strategy.
  12. Optimization goal.
  13. Co-evolving Solution and Search Strategy
  14. Solution evolution under the current strategy
  15. Progress monitoring and strategy updates
  16. ...and 26 more sections

Figures (4)

  • Figure 1: Evolving the search strategy. (\ref{['fig:arch_a']}) System architecture. EvoX has two coupled loops: an inner loop that evolves solutions, and an outer loop that evolves the search strategy that governs generation. (\ref{['fig:arch_b']}) Effect of search evolution. A strategy with fixed exploration-exploitation ratio (MAP-Elites, red) stagnates, while an evolving search strategy (blue) produces discrete performance breakthroughs.
  • Figure 2: Evolving search strategy on the signal processing task. Starting from a uniform random sampling strategy, EvoX detects stagnation and adaptively switches to greedy search, stratified multi-objective sampling, UCB-guided structural variation, and finally local refinement. These strategy changes enable discovery of improved filtering programs and yield major gains at iterations $\sim$48 (+0.119), $\sim$70 (+0.056), and $\sim$96 (+0.022), achieving 34.1% higher final score than the static baseline.
  • Figure 3: Algorithm and Research Challenges. EvoX achieves the highest average private performance with GPT-5 on 10 different ALE-Bench-Lite problems and highest median score across 172 different Frontier-CS challenges.
  • Figure 4: Search strategy evolution and cost-quality tradeoffs on the Heilbronn triangle task.(a) Dashed lines show fixed strategies, while solid lines show EvoX initialized from each strategy and allowed to evolve. Regardless of initialization, EvoX continues improving beyond the fixed strategy. (b) Cost-quality tradeoff under the GPT-5 model. To exceed a score of 0.031, EvoX and GEPA both require less than $1 in LLM generation cost, compared to ShinkaEvolve ($7.6) and OpenEvolve ($15.4).