DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
Mizanur Rahman, Mohammed Saidul, Md Tahmid, Shafiq Joty, and Enamul Hoque. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP-26) 2026.
PDF BibTex Slides