Foundations of Learning Reasoning Models

COLT 2026

Organizers: Nived Rajaraman, Nirmit Joshi, and Nati Srebro

Slides: PDF

Primary Papers

• Auto-Regressive Next-Token Predictors are Universal Learners Eran Malach ICML 2024
• A Theory of Learning with Autoregressive Chain of Thought Nirmit Joshi, Gal Vardi, Adam Block, Surbhi Goel, Zhiyuan Li, Theodor Misiakiewicz, Nathan Srebro COLT 2025
• CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision Awni Altabaa, Omar Montasser, John Lafferty NeurIPS 2025
• On Learning Verifiers and Implications to Chain-of-Thought Reasoning Maria-Florina Balcan, Avrim Blum, Zhiyuan Li, Dravyansh Sharma NeurIPS 2025
• The Coverage Principle: How Pre-Training Enables Post-Training Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Dylan J. Foster ICLR 2026
• Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum Nived Rajaraman, Audrey Huang, Miro Dudik, Robert Schapire, Dylan J. Foster, Akshay Krishnamurthy COLT 2026
• Learning to Think from Multiple Thinkers Nirmit Joshi, Roey Magen, Nathan Srebro, Nikolaos Tsilivis, Gal Vardi preprint

Other related papers

• Learning to Answer from Correct Demonstrations Nirmit Joshi, Gene Li, Siddharth Bhandari, Shiva Prasad Kasiviswanathan, Cong Ma, Nathan Srebro ICLR 2026
• Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan J. Foster ICML 2025
• Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End Steve Hanneke, Idan Mehalel, Shay Moran Preprint
• Online Learnability of Chain-of-Thought Verifiers: Soundness and Completeness Trade-offs Maria-Florina Balcan, Avrim Blum, Kiriaki Fragkia, Zhiyuan Li, Dravyansh Sharma Preprint
• Reward Learning from Best-of-N Preference Data: Targets, Tradeoffs, and Design Principles Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar Preprint