Test time scaling for LLMs is an emerging frontier that examines how large language models adapt and evolve their responses though reasoning abilities during inference. In recent years, LLMs have demonstrated significant progress in mimicking human-like reasoning—from basic pattern recognition to advanced problem-solving in mathematical contexts. In our social, titled “Test Time Scaling for LLMs,” we delve into the critical role of reasoning and cognitive thinking in LLMs, charting their evolution from earlier foundational works to the cutting-edge models of today. We invite researchers, practitioners, and enthusiasts to share insights and challenges, fostering a collaborative dialogue geared towards understanding the trade-offs between computational cost and reasoning quality. Moreover, we extend our conversation beyond pure mathematics to consider applications in other domains like medical diagnostics, where improved reasoning can lead to safer and more accurate outcomes. This session aims to inspire new ideas for leveraging test time scaling to drive the next wave of advancements in artificial intelligence.