{"ID":5439518,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T20:59:23.075938969Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30921","arxiv_id":"2606.30921","title":"Towards Transparent Checkpointing with AI-driven Code Generation","abstract":"Adding reliable checkpoint/restart support to an MPI scientific application is a time-consuming expert effort that requires deep knowledge of both the application and resilience. We ask whether a frontier large language model can perform this work end-to-end without human intervention. We assemble a benchmark suite of MPI applications spanning diverse domains and computation patterns, and drive an iterative code-generation loop for each application using Anthropic's Claude Opus 4.7 invoked through the OpenCode CLI. Across six scientific applications, the LLM generates working checkpoint/restart code in 50 minutes on average while consuming 3.4 M tokens per application. The generated code adds negligible overhead during normal failure-free execution on five of six applications and recovers from injected process failures with efficiency comparable to human-engineered checkpoint/restart implementations. These results suggest that automated end-to-end LLM-driven resilience engineering is technically viable today for a meaningful fraction of HPC applications.","short_abstract":"Adding reliable checkpoint/restart support to an MPI scientific application is a time-consuming expert effort that requires deep knowledge of both the application and resilience. We ask whether a frontier large language model can perform this work end-to-end without human intervention. We assemble a benchmark suite of...","url_abs":"https://arxiv.org/abs/2606.30921","url_pdf":"https://arxiv.org/pdf/2606.30921v1","authors":"[\"Hai Duc Nguyen\",\"Tekin Bicer\",\"Kyle Chard\",\"Ian Foster\",\"Bogdan Nicolae\"]","published":"2026-06-29T21:13:53Z","proceeding":"cs.DC","tasks":"[\"cs.DC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}