Journal article · 2025 · Open access
AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation
IEEE Transactions on Software Engineering, 52(2), 631–650 · Published 12 December 2025 · DOI 10.1109/tse.2025.3642621
In brief
“AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation” is a 2025 journal article by Yueheng Zhu and 6 co-authors, published in IEEE Transactions on Software Engineering. OpenAlex counts 19 citations as of 17 November 2026, which puts it in the top 7% of works published in 2025 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 19
- Most cited in
- 2026 (17)
- Field-weighted impact
- 9.23
- References
- 54
- Authors
- 7
Abstract
Recently, researchers have proposed many multi-agent frameworks for function-level code generation, which aim to improve software development productivity by automatically generating function-level source code based on task descriptions. A typical multi-agent framework consists of Large Language Model (LLM)-based agents that are responsible for task planning, code generation, testing, debugging, etc. Studies have shown that existing multi-agent code generation frameworks perform well on ChatGPT. However, their generalizability across other foundation LLMs remains unexplored systematically. In this paper, we report an empirical study on the generalizability of four state-of-the-art multi-agent code generation frameworks across 12 open-source LLMs with varying code generation and instruction-following capabilities. Our study reveals the unstable generalizability of existing frameworks on diverse foundation LLMs. Based on the findings obtained from the empirical study, we propose AdaCoder, a novel adaptive planning, multi-agent framework for function-level code generation. AdaCoder has two phases. Phase-1 is an initial code generation step without planning, which uses an LLM-based coding agent and a script-based testing agent to unleash LLM’s native power, identify cases beyond LLM’s power, and determine the errors hindering execution. Phase-2 adds a rule-based debugging agent and an LLM-based planning agent for iterative code generation with planning. Our evaluation shows that AdaCoder achieves higher generalizability on diverse LLMs. Compared to the best baseline MapCoder, AdaCoder is on average 27.69% higher in Pass@1, 16 times faster in inference, and 12 times lower in token consumption.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhu, Y., Liu, C., He, X., Ren, X., Liu, Z., Pan, R., & Zhang, H. (2025). AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation. IEEE Transactions on Software Engineering, 52(2), 631–650. https://doi.org/10.1109/tse.2025.3642621
MLA 9
Zhu, Yueheng, et al. “AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation.” IEEE Transactions on Software Engineering, vol. 52, no. 2, 2025, pp. 631–650. https://doi.org/10.1109/tse.2025.3642621.
Chicago
Zhu, Yueheng, Chao Liu, Xuan He, Xiaoxue Ren, Zhongxin Liu, Ruwei Pan, and Hongyu Zhang. 2025. “AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation.” IEEE Transactions on Software Engineering 52 (2): 631–650. https://doi.org/10.1109/tse.2025.3642621.
Harvard
Zhu, Y. et al. (2025) ‘AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation’, IEEE Transactions on Software Engineering, 52(2), pp. 631–650. doi:10.1109/tse.2025.3642621.
IEEE
Y. Zhu et al., “AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation,” IEEE Transactions on Software Engineering, vol. 52, no. 2, pp. 631–650, 2025, doi: 10.1109/tse.2025.3642621.
BibTeX
@article{zhu2025adacoder,
title = {{AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation}},
author = {Zhu, Yueheng and Liu, Chao and He, Xuan and Ren, Xiaoxue and Liu, Zhongxin and Pan, Ruwei and Zhang, Hongyu},
journal = {IEEE Transactions on Software Engineering},
year = {2025},
volume = {52},
number = {2},
pages = {631--650},
doi = {10.1109/tse.2025.3642621},
url = {https://doi.org/10.1109/tse.2025.3642621}
}
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
- multi-agent systems
- large language models
- adaptive planning
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?
Zhu, Y., Liu, C., He, X., Ren, X., Liu, Z., Pan, R., & Zhang, H. (2025). AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation. IEEE Transactions on Software Engineering, 52(2), 631–650. https://doi.org/10.1109/tse.2025.3642621
How many times has this paper been cited?
19 times, according to OpenAlex on 17 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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Yueheng Zhu, Chao Liu, Xuan He, Xiaoxue Ren, Zhongxin Liu, Ruwei Pan, Hongyu Zhang.
What is the DOI of this paper?
10.1109/tse.2025.3642621, permanently at https://doi.org/10.1109/tse.2025.3642621. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 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.