Yingbin Liang

Abstract While task-specific demonstrations show early success in using large language models (LLMs) to automate astronomical research tasks, they offer only partial views of the capabilities needed to solve astronomy problems, calling for a more thorough understanding of LLMs’ strengths and limitations. Existing benchmarks largely focus on simple question-answering, testing astronomical knowledge rather than the complex reasoning required in real research.

Conflicts of Interest The authors declare no conflicts of interest. Data Availability Statement All data is presented in the manuscript. References 1, , , , and , “Interface and Performance of 3D Printed Continuous Carbon Fiber Reinforced PLA Composites,” Composites Part A: Applied Science and Manufacturing 88 (2016): 198–205, https://doi.org/10.1016/j.compositesa.2016.05.032.