Atharv Sonwane, Eng-Shen Tu, Wei-Chung Lu, Claas Beger, Carter Larsen, Debjit Dhar, Simon Alford, Rachel Chen, Ronit Pattanayak, Tuan Anh Dang, Guohao Chen, Gloria Geng, Kevin Ellis, Saikat Dutta 0001. OmniCode: A Benchmark for Evaluating Software Development Agents. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 40634-40661, Association for Computational Linguistics, 2026. [doi]
@inproceedings{SonwaneTLBLDACP26,
title = {OmniCode: A Benchmark for Evaluating Software Development Agents},
author = {Atharv Sonwane and Eng-Shen Tu and Wei-Chung Lu and Claas Beger and Carter Larsen and Debjit Dhar and Simon Alford and Rachel Chen and Ronit Pattanayak and Tuan Anh Dang and Guohao Chen and Gloria Geng and Kevin Ellis and Saikat Dutta 0001},
year = {2026},
url = {https://aclanthology.org/2026.findings-acl.2020/},
researchr = {https://researchr.org/publication/SonwaneTLBLDACP26},
cites = {0},
citedby = {0},
pages = {40634-40661},
booktitle = {Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026},
editor = {Maria Liakata and Viviane P. Moreira and Jiajun Zhang 0001 and David Jurgens},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-395-1},
}