{"ID":2882556,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11110","arxiv_id":"2508.11110","title":"Diffusion is a code repair operator and generator","abstract":"Code diffusion models generate code by iteratively removing noise from the latent representation of a code snippet. During later steps of the diffusion process, when the code snippet has almost converged, differences between discrete representations of these snippets look like last-mile repairs applied to broken or incomplete code. We evaluate the extent to which this resemblance can be exploited to leverage pre-trained code diffusion models for the problem of last-mile repair by considering two applications with significant potential. First, we can leverage the diffusion model for last-mile repair by adding noise to a broken code snippet and resuming the diffusion process. Second, we can leverage the diffusion model to generate arbitrary amount of training data for last-mile repair tasks (that are computationally more efficient) by sampling an intermediate program (input) and the final program (output) from the diffusion process. We perform experiments on 3 domains (Python, Excel and PowerShell) to evaluate applications, as well as analyze properties.","short_abstract":"Code diffusion models generate code by iteratively removing noise from the latent representation of a code snippet. During later steps of the diffusion process, when the code snippet has almost converged, differences between discrete representations of these snippets look like last-mile repairs applied to broken or inc...","url_abs":"https://arxiv.org/abs/2508.11110","url_pdf":"https://arxiv.org/pdf/2508.11110v1","authors":"[\"Mukul Singh\",\"Gust Verbruggen\",\"Vu Le\",\"Sumit Gulwani\"]","published":"2025-08-14T23:27:09Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Diffusion Model\"]","has_code":false}