How Does Chain-of-Thought Supervision Teach Models to Reason? A Theoretical Analysis
cs.LG, cond-mat.dis-nn, stat.ML
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/taka255/theory_of_cot_in_training
Terminology
Sources
- Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
- The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
- Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
- Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
- An Asymptotic Theory of Chain-of-Thought in In-Context Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis