About Me
Hi!
I'm a PhD student in Computer Science at Virginia Tech, advised by Prof. Chandan Reddy. My research interests are centered around self evolving agents and their applications for scientific discovery, security of LLM systems and openendedness.
Before starting my Ph.D., I completed my undergraduate degree in Computer Science at BITS Pilani, India.
Along the journey of PhD, I’ve had the opportunity to collaborate with brilliant researchers whose mentorship and collaboration has significantly shaped my research journey: Chandan Reddy (VT), Parshin Shojaee (Apple), Ninareh Mehrabi (Meta), Akshita Jha (Apple), Ruoxi Jia (VT), and Nurendra Choudhary (Amazon).
Research Interests
My research studies how LLM-based agents can sustain progress in complex settings that require continual exploration rather than fast convergence. I design systems that generate hypotheses, evaluate their own failures, and update their strategies at test time using programmatic feedback loops and structured evaluation.
I am particularly interested in:
- Scientific discovery, where agents iteratively refine hypotheses, design experiments or queries, and adapt search strategies under feasibility and budget constraints.
- Red teaming of LLM systems, where agents must diversify attacks, reason about defenses, and adapt to changing policies and evaluators while operating under strict query budgets.
- Open-ended behavior, where maintaining novelty, diversity, and adaptability over long horizons is essential, and where premature convergence and reward exploitation are core failure modes.
News
- May 2026 Started my internship at Amazon Science working on Hypothesis Generation and Iterative Model Refinement.
- Apr 2026 Our paper Decaevolve was accepted at ICML 2026.
- Jan 2026 Our paper LLEMA was accepted at ICLR 2026.
- Mar 2026 Our paper SurfaceBench was accepted at TMLR.