3 papers
cs.AI2026
Agentic Retrieval and Reinforcement Learned Equation Chains: A Controlled Generation Framework for Complex and Novel Physics Word Problems
Tirthankar Mittra
Generating high-quality Physics Word Problems (PWPs) that are novel, complex, and solvable remains a challenging and underexplored problem in educational content generation. Existi…
cs.CL2026
Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement Learning
Tirthankar Mittra
In this paper, we build a reinforcement learning framework to study how children compose numbers using base-ten blocks. Studying numerical cognition in toddlers offers a powerful w…
cs.LG2024
Utilizing Lyapunov Exponents in designing deep neural networks
Tirthankar Mittra
Training large deep neural networks is resource intensive. This study investigates whether Lyapunov exponents can accelerate this process by aiding in the selection of hyperparamet…