Author name: Steve Hanneke, Idan Mehalel, Shay Moran

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

Steve Hanneke, Idan Mehalel, Shay Moran / April 21, 2026

arXiv:2604.12013v2 Announce Type: replace
Abstract: Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework fo…

cs.LG

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

Steve Hanneke, Idan Mehalel, Shay Moran / April 15, 2026

arXiv:2604.12013v1 Announce Type: new
Abstract: Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework for ne…