Seminars

Abstract: Large language models (LLMs) are increasingly deployed as reasoning engines, yet their practical use remains constrained by three persistent challenges: achieving high-quality reasoning at low cost, measuring performance reliably, and ensuring efficient, reproducible deployment. In this talk, I will present a research agenda addressing these challenges through new methods, benchmarks, and systems for practical LLM reasoning. I… Read More »Towards Reliable LLM Reasoning: Coordinated Agents, Variance-Aware Evaluation, and Lean Inference by Prof. Akhil Arora