EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0

TL;DR

EvoGraph is a framework that enables self-evolving software systems by representing artifacts as directed graphs, applying learned mutation operators, and selecting optimal variants, demonstrating significant improvements in security, translation, and documentation updates.

Contribution

EvoGraph introduces a novel graph-based representation and learned mutation operators for automated software evolution, enabling continuous adaptation and modernization of legacy codebases.

Findings

Fixes 83% of security vulnerabilities

Translates COBOL to Java with 93% functional equivalence

Maintains documentation freshness within two minutes

Abstract

We introduce **EvoGraph**, a framework that enables software systems to evolve their own source code, build pipelines, documentation, and tickets. EvoGraph represents every artefact in a typed directed graph, applies learned mutation operators driven by specialized small language models (SLMs), and selects survivors with a multi-objective fitness. On three benchmarks, EvoGraph fixes 83% of known security vulnerabilities, translates COBOL to Java with 93% functional equivalence (test verified), and maintains documentation freshness within two minutes. Experiments show a 40% latency reduction and a sevenfold drop in feature lead time compared with strong baselines. We extend our approach to **evoGraph**, leveraging language-specific SLMs for modernizing .NET, Lisp, CGI, ColdFusion, legacy Python, and C codebases, achieving 82-96% semantic equivalence across languages while reducing computational costs by 90% compared to large language models. EvoGraph's design responds to empirical failure modes in legacy modernization, such as implicit contracts, performance preservation, and integration evolution. Our results suggest a practical path toward Software 3.0, where systems adapt continuously yet remain under measurable control.