Papers by Mahesh Reddy Konatham
Journal of Information Systems Engineering and Management, 2025
A new framework for adaptive model context protocols that improve multi-agent cooperation in disp... more A new framework for adaptive model context protocols that improve multi-agent cooperation in dispersed environments is presented in this study. The suggested method makes use of dynamic context sharing mechanisms that adjust to task complexity, communication band-width, and computational limitations. The framework allows agents to negotiate the best parameters for information exchange by implementing a hierarchical context model with bidirectional context flow. In comparison to static approaches, the adaptive protocol lowers communication overhead while preserving task performance, as demonstrated by experimental evaluation in distributed sensor networks, autonomous vehicle coordination, and collaborative problem-solving. In order to intelligently filter information exchange, the framework presents context relevance scoring and selective propagation techniques. By providing solutions for autonomous systems functioning under fluctuating resource constraints, this research fills the gap between multi-agent collaboration and distributed systems optimization.
Journal of Information Systems Engineering and Management, 2025
The rapid advancements in autonomous systems, such as self-driving cars, drones, and robotics, ha... more The rapid advancements in autonomous systems, such as self-driving cars, drones, and robotics, have highlighted the need for scalable deep learning models that can support real-time decisionmaking. However, the implementation of deep learning in these systems is challenged by issues of scalability, computational efficiency, and real-time data processing. This paper explores the latest techniques for scaling deep learning models to meet the stringent demands of autonomous systems. We discuss recent advancements in reinforcement learning, model optimization, and edge computing, focusing on their ability to facilitate decision-making in resource-constrained environments. Additionally, we examine case studies from various autonomous systems to highlight the application of scalable models in real-world settings. The findings suggest that future advancements in model compression, distributed learning, and hybrid architectures will be key to overcoming current challenges. The paper concludes with potential research directions, including the integration of quantum computing and neuromorphic systems, to further enhance the scalability and efficiency of real-time decision-making in autonomous systems.
Uploads
Papers by Mahesh Reddy Konatham