KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation

TL;DR

KCoEvo introduces a knowledge graph-augmented framework that enhances code evolution and API migration by modeling API changes and guiding code generation, significantly outperforming standard language models.

Contribution

The paper presents a novel framework combining static and dynamic API graphs with LLMs, improving code migration accuracy and scalability with minimal supervision.

Findings

Significant improvement in migration accuracy over LLM baselines

Effective modeling of intra- and cross-version API transitions

Scalable approach with minimal human supervision

Abstract

Code evolution is inevitable in modern software development. Changes to third-party APIs frequently break existing code and complicate maintenance, posing practical challenges for developers. While large language models (LLMs) have shown promise in code generation, they struggle to reason without a structured representation of these evolving relationships, often leading them to produce outdated APIs or invalid outputs. In this work, we propose a knowledge graph-augmented framework that decomposes the migration task into two synergistic stages: evolution path retrieval and path-informed code generation. Our approach constructs static and dynamic API graphs to model intra-version structures and cross-version transitions, enabling structured reasoning over API evolution. Both modules are trained with synthetic supervision automatically derived from real-world API diffs, ensuring scalability and minimal human effort. Extensive experiments across single-package and multi-package benchmarks demonstrate that our framework significantly improves migration accuracy, controllability, and execution success over standard LLM baselines. The source code and datasets are available at: https://github.com/kangjz1203/KCoEvo.