ReCode: Updating Code API Knowledge with Reinforcement Learning
Haoze Wu, Yunzhi Yao, Wenhao Yu, Ningyu Zhang
Abstract
Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their training data, even with access to current documentation, impedes reliable code generation in dynamic environments. To tackle this issue, we propose ReCode (rule-based Reinforcement learning for Code Update), a novel framework that mimics human programmer adaptation to API changes. Specifically, we construct a dataset of approximately 2,000 data entries to train the LLMs to perform version migration based on updated information. Then, we introduce a modified string similarity metric for code evaluation as the reward for reinforcement learning. Our experiments demonstrate that ReCode substantially boosts LLMs
BibTeX
@inproceedings{aaai2026_recodeupdatingco,
title = {ReCode: Updating Code API Knowledge with Reinforcement Learning},
author = {Haoze Wu and Yunzhi Yao and Wenhao Yu and Ningyu Zhang},
booktitle = {AAAI 2026},
year = {2026}
}