Kavana Venkatesh
👋 Hi there — welcome to my corner of the internet!
Kavana Venkatesh
Building self-evolving agentic systems — studying agent harnesses, multi-agent coordination, and the safety and interpretability of LLM agents.
I am a PhD student at Virginia Tech, affiliated with the Sanghani Center for Artificial Intelligence and Data Analytics. I am fortunate to be advised by Dr. Jiaming Cui. Previously, I earned my master's degree in Data Science from Northeastern University, Boston. When I'm not busy exploring AI frontiers, you might find me geeking out over LLM agents, enjoying fun books, or perfecting my latest cup of coffee. ☕
A few fun things about me:
- 🌍 I love traveling and capturing stories through photography.
- 🐾 Obsessed with pets, especially dogs.
- 📚 Passionate about storytelling and making AI more accessible to everyone.
Feel free to explore my work, and reach out if you'd like to collaborate or just chat about AI and beyond! 😊
🔬 What I work on
My research centers on agentic AI — designing agents that evolve, coordinate, and reason reliably. I aim to build interpretable and dependable agentic systems to enable safe consumption of AI at scale across diverse domains.
Self-Evolving Agents
Agents that adapt, improve, and specialize over time.
Agent Harnesses & Tool Use
Orchestration and reliable tool-augmented reasoning in LLM-based systems.
Multi-Agent Systems
Coordination and collective cognition across agent societies.
Agent Safety & Interpretability
Monitoring, attribution, and cascade-attack detection for LLM agents.
Evaluation & Benchmarking
Dependable evaluation frameworks for complex agentic systems.