Large Language Model-Based Agents for Software Engineering: A Survey. Liu, J., Wang, K., Chen, Y., Peng, X., Chen, Z., Zhang, L., & Lou, Y. December, 2025. arXiv:2409.02977 [cs]![Large Language Model-Based Agents for Software Engineering: A Survey [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 124 papers and categorize them from two perspectives, i.e., the SE and agent perspectives. In addition, we discuss open challenges and future directions in this critical domain. The repository of this survey is at https://github.com/FudanSELab/Agent4SE-Paper-List.
@misc{liu_large_2025,
title = {Large {Language} {Model}-{Based} {Agents} for {Software} {Engineering}: {A} {Survey}},
shorttitle = {Large {Language} {Model}-{Based} {Agents} for {Software} {Engineering}},
url = {http://arxiv.org/abs/2409.02977},
doi = {10.48550/arXiv.2409.02977},
abstract = {The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 124 papers and categorize them from two perspectives, i.e., the SE and agent perspectives. In addition, we discuss open challenges and future directions in this critical domain. The repository of this survey is at https://github.com/FudanSELab/Agent4SE-Paper-List.},
language = {en},
urldate = {2026-01-14},
publisher = {arXiv},
author = {Liu, Junwei and Wang, Kaixin and Chen, Yixuan and Peng, Xin and Chen, Zhenpeng and Zhang, Lingming and Lou, Yiling},
month = dec,
year = {2025},
note = {arXiv:2409.02977 [cs]},
keywords = {/unread, Computer Science - Artificial Intelligence, Computer Science - Software Engineering},
}
Downloads: 0
{"_id":"kiktWiTvbzvjEiMHi","bibbaseid":"liu-wang-chen-peng-chen-zhang-lou-largelanguagemodelbasedagentsforsoftwareengineeringasurvey-2025","author_short":["Liu, J.","Wang, K.","Chen, Y.","Peng, X.","Chen, Z.","Zhang, L.","Lou, Y."],"bibdata":{"bibtype":"misc","type":"misc","title":"Large Language Model-Based Agents for Software Engineering: A Survey","shorttitle":"Large Language Model-Based Agents for Software Engineering","url":"http://arxiv.org/abs/2409.02977","doi":"10.48550/arXiv.2409.02977","abstract":"The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 124 papers and categorize them from two perspectives, i.e., the SE and agent perspectives. In addition, we discuss open challenges and future directions in this critical domain. The repository of this survey is at https://github.com/FudanSELab/Agent4SE-Paper-List.","language":"en","urldate":"2026-01-14","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Liu"],"firstnames":["Junwei"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Kaixin"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Yixuan"],"suffixes":[]},{"propositions":[],"lastnames":["Peng"],"firstnames":["Xin"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Zhenpeng"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Lingming"],"suffixes":[]},{"propositions":[],"lastnames":["Lou"],"firstnames":["Yiling"],"suffixes":[]}],"month":"December","year":"2025","note":"arXiv:2409.02977 [cs]","keywords":"/unread, Computer Science - Artificial Intelligence, Computer Science - Software Engineering","bibtex":"@misc{liu_large_2025,\n\ttitle = {Large {Language} {Model}-{Based} {Agents} for {Software} {Engineering}: {A} {Survey}},\n\tshorttitle = {Large {Language} {Model}-{Based} {Agents} for {Software} {Engineering}},\n\turl = {http://arxiv.org/abs/2409.02977},\n\tdoi = {10.48550/arXiv.2409.02977},\n\tabstract = {The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 124 papers and categorize them from two perspectives, i.e., the SE and agent perspectives. In addition, we discuss open challenges and future directions in this critical domain. The repository of this survey is at https://github.com/FudanSELab/Agent4SE-Paper-List.},\n\tlanguage = {en},\n\turldate = {2026-01-14},\n\tpublisher = {arXiv},\n\tauthor = {Liu, Junwei and Wang, Kaixin and Chen, Yixuan and Peng, Xin and Chen, Zhenpeng and Zhang, Lingming and Lou, Yiling},\n\tmonth = dec,\n\tyear = {2025},\n\tnote = {arXiv:2409.02977 [cs]},\n\tkeywords = {/unread, Computer Science - Artificial Intelligence, Computer Science - Software Engineering},\n}\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Liu, J.","Wang, K.","Chen, Y.","Peng, X.","Chen, Z.","Zhang, L.","Lou, Y."],"key":"liu_large_2025","id":"liu_large_2025","bibbaseid":"liu-wang-chen-peng-chen-zhang-lou-largelanguagemodelbasedagentsforsoftwareengineeringasurvey-2025","role":"author","urls":{"Paper":"http://arxiv.org/abs/2409.02977"},"keyword":["/unread","Computer Science - Artificial Intelligence","Computer Science - Software Engineering"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"misc","biburl":"https://bibbase.org/zotero/maraee75","dataSources":["PjpadRRabZA7FRKpn"],"keywords":["/unread","computer science - artificial intelligence","computer science - software engineering"],"search_terms":["large","language","model","based","agents","software","engineering","survey","liu","wang","chen","peng","chen","zhang","lou"],"title":"Large Language Model-Based Agents for Software Engineering: A Survey","year":2025}