A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
cs.LG
Submitted: 2026-05-07
Updated: 2026-11-15
Terminology
Sources
- CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
- Deterministic Apple Tasting
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- The Llama 3 Herd of Models
- Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
- Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
- OpenAI o1 System Card
- Learning to Think from Multiple Thinkers: How Chain-of-Thought Heterogeneity Affects Efficient Learnability
- A Theory of Learning with Autoregressive Chain of Thought
- Transformers Provably Solve Parity Efficiently with Chain of Thought
- Auto-Regressive Next-Token Predictors are Universal Learners
- The Expressive Power of Transformers with Chain of Thought
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- The Probably Approximately Correct Learning Model in Computational Learning Theory
- How Reinforcement Learning After Next-Token Prediction Facilitates 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