Tanay Dixit

Hi, I'm Tanay - an ML Engineer at Adobe on the Experience Platform Agent Orchestrator, focused on memory and personalization for our agents and the eval harnesses that drive our hill-climbing loop.

I graduated with an MS in Computer Science from the University of Illinois, Urbana-Champaign, where I worked with Prof. Jiawei Han. I am honoured to be a Siebel Scholar (Class of 2025). I graduated from the Indian Institute of Technology Madras in 2023 with a bachelor's degree in ECE, where I worked with Prof. Mitesh Khapra. I have first-author papers at ACL, EMNLP, and WWW on multi-agent systems and evaluation frameworks (1200+ citations).

• Agentic Systems: Developed a multi-agent system that autonomously searches and suggests Wikipedia updates from online sources [1].
• Evaluations & Applications: Built an interactive tool for performing LLM prompt migrations efficiently [1]. Increased the usability and interpretability of LLM-based NL2SQL pipelines by introducing intermediate representations [2]. Showed NLG metrics contain several evaluation blind spots and proposed a better framework to meta-evaluate metrics [3]. Released a large meta-evaluation dataset and metrics for low-resource translation evaluation [4]
• Interpretability & Trustworthiness: Developed a retrieval augmented counterfactual data generation techniques to improve model generalization [5] , and improved the factuality of summarization systems by training models using a ranking loss [6]

Email  /  LinkedIn  /  Google Scholar  /  Semantic Scholar

Template from here