ReCast: שימור חוזה-מוגן לתקשורת מולטימדיה קבועה

תקציר מקורי באנגליתarXiv:2610.01184v1 Announce Type: cross Abstract: Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media fro