Indian researcher Kunvar Thaman's solo-authored paper has been accepted at the International Conference on Machine Learning (ICML) 2026, a conference typically dominated by firms like OpenAI and Google. His paper 'Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use' studies how LLM agents exploit shortcuts in multi-step tasks. Thaman is an alumnus of BITS Pilani.