Conference paper · 2026 · Open access
ReCode: Updating Code API Knowledge with Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 33908–33916 · Published 14 March 2026 · DOI 10.1609/aaai.v40i40.40683
In brief
“ReCode: Updating Code API Knowledge with Reinforcement Learning” is a 2026 conference paper by Haoze Wu and 3 co-authors, published in Proceedings of the AAAI Conference on Artificial Intelligence. OpenAlex counts 16 citations as of 19 November 2026, which puts it in the top 7% of works published in 2026 by citations. It is open access: the full text is free to read at Proceedings of the AAAI Conference on Artificial Intelligence.
- Citations
- 16
- Most cited in
- 2026 (14)
- Field-weighted impact
- 18.18
- References
- 66
- Authors
- 4
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 This critical limitation, stemming from reliance on outdated API knowledge from their training data, even with access to current documentation, impedes reliable code generation in dynamic environments.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' code generation performance in dynamic API scenarios, especially on the unseen CodeUpdateArena task. Crucially, compared to supervised fine-tuning, ReCode has less impact on LLMs' general code generation abilities. We apply ReCode on various LLMs and reinforcement learning algorithms (GRPO and DAPO), all achieving consistent improvements. Notably, after training, Qwen2.5-Coder-7B outperforms that of the 32B parameter code instruction-tuned model and the reasoning model with the same architecture.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wu, H., Yao, Y., Yu, W., & Zhang, N. (2026). ReCode: Updating Code API Knowledge with Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 33908–33916. https://doi.org/10.1609/aaai.v40i40.40683
MLA 9
Wu, Haoze, et al. “ReCode: Updating Code API Knowledge with Reinforcement Learning.” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 40, 2026, pp. 33908–33916. https://doi.org/10.1609/aaai.v40i40.40683.
Chicago
Wu, Haoze, Yunzhi Yao, Wenhao Yu, and Ningyu Zhang. 2026. “ReCode: Updating Code API Knowledge with Reinforcement Learning.” Proceedings of the AAAI Conference on Artificial Intelligence 40 (40): 33908–33916. https://doi.org/10.1609/aaai.v40i40.40683.
Harvard
Wu, H. et al. (2026) ‘ReCode: Updating Code API Knowledge with Reinforcement Learning’, Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), pp. 33908–33916. doi:10.1609/aaai.v40i40.40683.
IEEE
H. Wu, Y. Yao, W. Yu, and N. Zhang, “ReCode: Updating Code API Knowledge with Reinforcement Learning,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 40, pp. 33908–33916, 2026, doi: 10.1609/aaai.v40i40.40683.
BibTeX
@inproceedings{wu2026recode,
title = {{ReCode: Updating Code API Knowledge with Reinforcement Learning}},
author = {Wu, Haoze and Yao, Yunzhi and Yu, Wenhao and Zhang, Ningyu},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {40},
pages = {33908--33916},
doi = {10.1609/aaai.v40i40.40683},
url = {https://doi.org/10.1609/aaai.v40i40.40683}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- large language models
- code generation
- reinforcement learning
- reward function design
- Qwen2.5-Coder
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wu, H., Yao, Y., Yu, W., & Zhang, N. (2026). ReCode: Updating Code API Knowledge with Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 33908–33916. https://doi.org/10.1609/aaai.v40i40.40683
How many times has this paper been cited?
16 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Proceedings of the AAAI Conference on Artificial Intelligence: sign in and open the full text from this page.
Who wrote this paper?
Haoze Wu, Yunzhi Yao, Wenhao Yu, Ningyu Zhang.
What is the DOI of this paper?
10.1609/aaai.v40i40.40683, permanently at https://doi.org/10.1609/aaai.v40i40.40683. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.