GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

2025-11-17

AI Summary

Existing LLM-guided evolutionary algorithms (e.g., AlphaEvolve) lack implementation details, severely hindering reproducibility and methodological extension. To address this, we introduce the first open-source, modular LLM-driven evolutionary computation framework. Our approach features: (1) an LLM-powered mutation operator with bidirectional lineage tracking, enabling generative insight generation tightly coupled with dynamic evolutionary process control; (2) a declarative, asynchronous DAG-based evaluation architecture supporting quality diversity (MAP-Elites), multi-island strategies, and asynchronous evolution; and (3) full reproduction and outperformance of AlphaEvolve on benchmark problems—including Heilbronn triangle, circle packing, and high-dimensional kissing number optimization. All code, configuration files, and experimental logs are publicly released. This work significantly advances reproducibility, extensibility, and iteration efficiency in LLM-augmented evolutionary algorithm research.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Evolutionary Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Recent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering novel mathematical constructions and solving challenging optimization problems. However, the high-level descriptions in published work leave many implementation details unspecified, hindering reproducibility and further research. In this report we present GigaEvo, an extensible open-source framework that enables researchers to study and experiment with hybrid LLM-evolution approaches inspired by AlphaEvolve. Our system provides modular implementations of key components: MAP-Elites quality-diversity algorithms, asynchronous DAG-based evaluation pipelines, LLM-driven mutation operators with insight generation and bidirectional lineage tracking, and flexible multi-island evolutionary strategies. In order to assess reproducibility and validate our implementation we evaluate GigaEvo on challenging problems from the AlphaEvolve paper: Heilbronn triangle placement, circle packing in squares, and high-dimensional kissing numbers. The framework emphasizes modularity, concurrency, and ease of experimentation, enabling rapid prototyping through declarative configuration. We provide detailed descriptions of system architecture, implementation decisions, and experimental methodology to support further research in LLM driven evolutionary methods. The GigaEvo framework and all experimental code are available at https://github.com/AIRI-Institute/gigaevo-core.

Problem

• Addresses reproducibility gaps in LLM-evolutionary algorithm research implementations
• Provides modular framework for hybrid LLM-evolution optimization experiments
• Validates implementation on complex geometric and mathematical optimization problems

Innovation

• Open-source framework combines LLMs with evolution algorithms
• Modular components include quality-diversity and LLM mutation operators
• Flexible evolutionary strategies with declarative configuration support