MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641088964 A) filed by Dr Prof Chhaya Surbhayan Dule; Dr Prof Rajasekharaiah K. M; and Dr. Vimala Roselin J on July 21, 2026, for Autonomous Software Testing Framework Using Multi-Agent Artificial Intelligence.
Inventors include Dr Prof Chhaya Surbhayan Dule; Dr Prof Rajasekharaiah K. M; and Dr. Vimala Roselin J.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: ABSTRACT Autonomous Software Testing Framework Using Multi-Agent Artificial Intelligence The present invention relates to an **Autonomous Software Testing Framework Using Multi-Agent Artificial Intelligence (MAAI)** designed to automate, optimize, and continuously improve the software testing lifecycle across modern applications. The framework employs a collaborative ecosystem of intelligent software agents, each assigned specialized responsibilities including requirement analysis, test case generation, test data synthesis, execution scheduling, defect detection, regression analysis, performance evaluation, security validation, and report generation. A central coordination agent orchestrates communication among distributed agents using reinforcement learning, knowledge sharing, and adaptive decision-making to maximize testing efficiency while minimizing execution time and resource consumption. The proposed framework integrates machine learning, natural language processing, large language models, and static and dynamic code analysis to automatically interpret software requirements, identify critical functional paths, generate comprehensive test suites, and prioritize test execution based on code changes and historical defect patterns. The system continuously learns from previous testing outcomes through feedback-driven optimization, enabling autonomous refinement of testing strategies and improved defect prediction accuracy over successive software releases. The framework supports cloud-native, web, mobile, desktop, embedded, and microservices-based applications while seamlessly integrating with Continuous Integration and Continuous Deployment (CI/CD) pipelines for real-time quality assurance. Advanced anomaly detection mechanisms identify hidden defects, security vulnerabilities, performance bottlenecks, and compliance violations before software deployment. Distributed execution agents dynamically allocate testing workloads across heterogeneous computing environments to reduce testing latency and enhance scalability. The invention further incorporates explainable AI techniques to provide transparent reasoning for generated test cases and detected defects, thereby improving developer trust and debugging efficiency. Experimental implementation demonstrates significant improvements in test coverage, defect detection rate, execution speed, resource utilization, and maintenance efficiency compared with conventional automated testing systems, making the proposed framework a scalable, intelligent, and self-adaptive solution for next-generation software quality assurance in rapidly evolving software development environments.
Disclaimer: Curated by HT Syndication.
