MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641101612 A) filed by Dr. V. Brinda Shree; Dr. Poonam Saini; Aavleen Bakshi; Sowmya P; Dr. G. Manikandan; Dr. J. Srinivasan; Dr. B. Ujwala; Mukesh Kumar Patel; Dr. Prabhu Dayal Sharma; Thulasimani T; V. Pavithra; and Maheshwari R on August 22, 2026, for Ai Agentic Framework For Personalized Curriculum Recommendation And Adaptive Student Performance Enhancement In Higher Education.
Inventors include Dr. V. Brinda Shree; Dr. Poonam Saini; Aavleen Bakshi; Sowmya P; Dr. G. Manikandan; Dr. J. Srinivasan; Dr. B. Ujwala; Mukesh Kumar Patel; Dr. Prabhu Dayal Sharma; Thulasimani T; V. Pavithra; and Maheshwari R.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: AI Agentic Framework for Personalized Curriculum Recommendation and Adaptive Student Performance Enhancement in Higher Education is the proposed invention. The proposed invention discloses an AI Agentic Framework for Personalized Curriculum Recommendation and Adaptive Student Performance Enhancement in Higher Education based on a Multi-Agent Reinforcement Learning (MARL) architecture. The framework comprises autonomous AI agents configured for student profiling, curriculum analysis, skill-gap detection, curriculum recommendation, performance monitoring, and academic intervention. A multi-agent decision engine coordinates the agents to determine personalized educational actions using a reinforcement-based reward mechanism incorporating academic performance improvement, competency attainment, course completion, workload balance, learning-gap reduction, and achievement of program learning outcomes. The system continuously receives student academic records, learning activities, assessment results, competency information, and curriculum requirements to generate dynamic learner states. Recommended courses, learning resources, assessments, and interventions are delivered through an educational platform, while subsequent student responses are monitored and returned to the reinforcement-learning environment for policy adaptation. The invention thereby provides an autonomous closed-loop framework capable of continuously optimizing individualized curriculum pathways and improving student academic performance in higher educational institutions.
Disclaimer: Curated by HT Syndication.
