Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches

ArXi:2602.08561v2 Announce Type: replace-cross Reproducing computational research is often assumed to be as simple as rerunning the original code with provided data. In practice, missing packages, fragile file paths, version conflicts, or incomplete logic frequently cause analyses to fail, even when materials are shared. This study investigates whether large language models and AI agents can automate the diagnosis and repair of such failures, making computational results easier to reproduce and verify.