Software obfuscation, particularly prevalent in JavaScript, hinders code comprehension and analysis, posing significant challenges to software testing, static analysis, and malware detection. This pa- per introduces CASCADE, a novel hybrid approach that integrates the advanced coding capabilities of Gemini with the deterministic transformation capabilities of a compiler Intermediate Representa- tion (IR), specifically JavaScript IR (JSIR). By employing Gemini to identify critical prelude functions—the foundational components underlying the most prevalent obfuscation techniques—and leverag- ing JSIR for subsequent code transformations, CASCADE effectively recovers semantic elements like original strings and API names, and reveals original program behaviors. This method overcomes limita- tions of existing static and dynamic deobfuscation techniques, elim- inating hundreds to thousands of hard-coded rules while achieving reliability and flexibility. CASCADE is already deployed in Google’s production environment, demonstrating substantial improvements in JavaScript deobfuscation efficiency and reducing reverse engi- neering efforts.