Rules to Tools (R2T): executable checks for LLM agents in scientific computing (arXiv:2610.00313v1)

KEY POINTS

1. The arXiv preprint introduces Rules to Tools (R2T), a workflow that supplies prepared executable checks of public scientific requirements for LLM-based scientific-coding agents.
2. In matched SciCode repair-group experiments, teams sharing written checks, starting programs, model and budgets gave a callable implementation to a tool group; across two task-ID cohorts prepared checks achieved 29/30 complete repairs versus 26/30 for detailed text, with mixed task-level outcomes (three task IDs favor tools, one favors text, eleven tie) and a reported task-cluster bootstrap 95% interval of [-12.5, 43.75] percentage points for the difference; other cohorts and PDE comparisons show small, task-dependent differences in success rates and changes in agent-side output and public CPU use.
3. Prepared executable checks change repair success rates and agent-side costs in measurable, task-dependent ways, informing how tool interfaces can be used to validate and reduce model outputs in scientific coding workflows.