MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511113899 A) filed by Ajay Kumar Garg Engineering College, Ghaziabad, Uttar Pradesh, on Nov. 19, 2025, for 'reinforcement-learning based addressing mode selection system.'
Inventor(s) include Mohammad Anas Khan; Muskan Raj; Naina Batra; Naitra Tyagi; Dr. Inderjeet Kaur; and Ms. Shraddha Pandey.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "Reinforcement-Learning Based Addressing Mode Selection System Abstract A compiler optimisation system (100) for AI-based addressing mode selection in code generation has been provided. Moreover a compiler framework (102) executed on a processing platform (104) enables generation of instructions for a hardware environment. Furthermore a feature extraction unit (106) within said compiler framework (102) encodes a code context (108) for a target instruction into a feature vector. Further a reinforcement learning agent structure (114) receives said feature vector and outputs an addressing mode decision for said target instruction. Moreover a feedback integration structure (118) receives performance data from execution of compiled code on a hardware environment and updates parameters associated with said reinforcement learning agent structure (114). Furthermore said system (100) enables adaptive selection of addressing modes informed by actual execution outcomes to enhance code-generation performance."
Disclaimer: Curated by HT Syndication.
