The Screen Is Not the State: Causally Grounded Artifact Critics for Office Agents

Office agents produce editable documents, spreadsheets, and presentations whose correctness depends on more than visible content. Required formulas, heading styles, or speaker notes may be absent even when a file appears correct. Such failures can violate one requirement while leaving others satisfied and different implementations may satisfy the same requirements. Reliable evaluation therefore requires both access to native file state and an understanding of which rubric judgments should change or remain stable after an edit. We introduce CARE, a rubric-conditioned artifact critic that combines native and rendered evidence with programmatically verified relation supervision. Its **locality** objective encourages sensitivity on affected rubrics and consistency on unaffected rubrics and **invariance** stabilizes predictions across reward-preserving implementations. Inference requires no golden artifact. Experiments on a verified DOCX, XLSX, and PPTX corpus show reduced drift across three held-out splits. In an ablation study, adding locality to pairwise reward modeling reduces unaffected-rubric drift from $0.226$ to $0.044$, and adding invariance reduces reward-preserving candidate-score drift from $0.096$ to $0.031$. These results show that relational supervision can improve response stability without necessarily improving classification or candidate selection.