Rajesh Mangannavar

I am a PhD student in Computer Science at Oregon State University, where I work on artificial intelligence and agentic systems. My research focuses on developing intelligent agents that can reason, plan, and act effectively in complex real-world environments.

My current work explores several key areas in AI:

• LLM-based multi-agent systems and orchestration for complex reasoning tasks
• Agentic AI with verifier-guided training and reinforcement learning from verification rewards (RLVR)
• Neural-symbolic planning combining graph neural networks with classical and hierarchical planners
• Scalable decision-making under uncertainty (POMDPs) with learned policies and value functions

I am particularly interested in developing AI agents that can learn from experience to handle increasingly complex tasks while generalizing effectively to new situations. My research combines techniques from large language models, reinforcement learning, symbolic planning, and deep learning to create more capable and adaptable autonomous systems.