Antibiotic resistance has become a growing worldwide concern as new resistance mechanisms are emerging and spreading globally, and thus detecting and collecting the cause – Antibiotic Resistance Genes (ARGs), have been more critical than ever. In this work, we aim to automate the curation of ARGs by extracting ARG-related assertive statements from scientific papers. To support the research towards this direction, we build SciARG, a new benchmark dataset containing 2,000 manually annotated statements as the evaluation set and 12,516 silver-standard training statements that are automatically created from scientific papers by a set of rules. To set up the baseline performance on SciARG, we exploit three state-of-the-art neural architectures based on pre-trained language models and prompt tuning, and further ensemble them to attain the highest 77.0% F-score. To the best of our knowledge, we are the first to leverage natural language processing techniques to curate all validated ARGs from scientific papers. Both the code and data are publicly available at https://github.com/VT-NLP/SciARG.