AI RESEARCH

Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End

arXiv CS.LG

ArXi:2604.12013v1 Announce Type: new Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi (COLT 2025) In this work we give a nearly complete answer to both questions by uncovering a taxonomy of how the sample complexity scales with $T