DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914288782802944 |
|---|---|
| author | Tang, Yuheng Zhu, Kaijie Ruan, Bonan Zhang, Chuqi Yang, Michael Li, Hongwei Guo, Suyue Shi, Tianneng Li, Zekun Kruegel, Christopher Vigna, Giovanni Song, Dawn Wang, William Yang Wang, Lun Ding, Yangruibo Liang, Zhenkai Guo, Wenbo |
| author_facet | Tang, Yuheng Zhu, Kaijie Ruan, Bonan Zhang, Chuqi Yang, Michael Li, Hongwei Guo, Suyue Shi, Tianneng Li, Zekun Kruegel, Christopher Vigna, Giovanni Song, Dawn Wang, William Yang Wang, Lun Ding, Yangruibo Liang, Zhenkai Guo, Wenbo |
| contents | Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps cycle in real-world software, including developing, deploying, and managing, requires analyzing large-scale projects, understanding dynamic program behaviors, leveraging domain-specific tools, and making sequential decisions. However, existing benchmarks focus on isolated problems and lack environments and tool interfaces for DevOps. We introduce DevOps-Gym, the first end-to-end benchmark for evaluating AI agents across core DevOps workflows: build and configuration, monitoring, issue resolving, and test generation. DevOps-Gym includes 700+ real-world tasks collected from 30+ projects in Java and Go. We develop a semi-automated data collection mechanism with rigorous and non-trivial expert efforts in ensuring the task coverage and quality. Our evaluation of state-of-the-art models and agents reveals fundamental limitations: they struggle with issue resolving and test generation in Java and Go, and remain unable to handle new tasks such as monitoring and build and configuration. These results highlight the need for essential research in automating the full DevOps cycle with AI agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20882 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle Tang, Yuheng Zhu, Kaijie Ruan, Bonan Zhang, Chuqi Yang, Michael Li, Hongwei Guo, Suyue Shi, Tianneng Li, Zekun Kruegel, Christopher Vigna, Giovanni Song, Dawn Wang, William Yang Wang, Lun Ding, Yangruibo Liang, Zhenkai Guo, Wenbo Software Engineering Artificial Intelligence Cryptography and Security Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps cycle in real-world software, including developing, deploying, and managing, requires analyzing large-scale projects, understanding dynamic program behaviors, leveraging domain-specific tools, and making sequential decisions. However, existing benchmarks focus on isolated problems and lack environments and tool interfaces for DevOps. We introduce DevOps-Gym, the first end-to-end benchmark for evaluating AI agents across core DevOps workflows: build and configuration, monitoring, issue resolving, and test generation. DevOps-Gym includes 700+ real-world tasks collected from 30+ projects in Java and Go. We develop a semi-automated data collection mechanism with rigorous and non-trivial expert efforts in ensuring the task coverage and quality. Our evaluation of state-of-the-art models and agents reveals fundamental limitations: they struggle with issue resolving and test generation in Java and Go, and remain unable to handle new tasks such as monitoring and build and configuration. These results highlight the need for essential research in automating the full DevOps cycle with AI agents. |
| title | DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle |
| topic | Software Engineering Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2601.20882 |