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struggle to reason without a structured representation of these evolving relationships, often leading them to produce outdated APIs or invalid outputs.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.
@article{arxiv.2603.07581,
title = {KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation},
author = {Jiazhen Kang and Yuchen Lu and Chen Jiang and Jinrui Liu and Tianhao Zhang and Bo Jiang and Ningyuan Sun and Tongtong Wu and Guilin Qi},
journal= {arXiv preprint arXiv:2603.07581},
year = {2026}
}