Nathani, Deepak

Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies

Pan, L., Saxon, M., Xu, W., Nathani, D., Wang, X., & Wang, W. Y. (2024) · Transactions of the Association for Computational Linguistics

Topic ModelingNatural Language Processing Techniques

Cited by 86

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Pan, L., Saxon, M., Xu, W., Nathani, D., Wang, X., & Wang, W. Y. (2023) · arXiv

Topic ModelingNatural Language Processing Techniques

Cited by 25

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Nathani, D., Madaan, L., Roberts, N., Bashlykov, N., Menon, A., Moens, V., Budhiraja, A., Magka, D., Vorotilov, V., Chaurasia, G., et al. (2025) · arXiv

Artificial Intelligence ApplicationsReinforcement Learning in Robotics

Cited by 15

Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

Weng, Z., Antoniades, A., Nathani, D., Zhang, Z., Pu, X., & Wang, X. E. (2026) · arXiv

Evolutionary Algorithms and ApplicationsSoftware Engineering Research

Cited by 0

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

Antoniades, A., Nathani, D., Saha, R., Amayuelas, A., Bercovich, I., Weng, Z., Baskaran, V., Bhatia, K., & Wang, W. Y. (2026) · arXiv

Evolutionary Algorithms and ApplicationsReinforcement Learning in Robotics

Cited by 0

Learning the ARTS of Search for Automated Discovery

Juneja, G., Jain, A. K., Nathani, D., Wang, W. Y., & Wang, X. E. (2026) · arXiv

AI-based Problem Solving and PlanningEvolutionary Algorithms and Applications

Cited by 0