Reasoning in LLMs Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Papers on reasoning capabilities of large language models — covering mathematical reasoning, tool augmentation, and inference-time scaling.

Reasoning in LLMs: 10 key papers

1. Training Verifiers to Solve Math Word Problems
   Cobbe et al. arXiv 2021.
2. Solving Quantitative Reasoning Problems with Language Models
   Lewkowycz et al. arXiv 2022.
3. Measuring Mathematical Problem Solving With the MATH Dataset
   Hendrycks et al. arXiv 2021.
4. Let's Verify Step by Step
   Lightman et al. arXiv 2023.
5. STaR: Bootstrapping Reasoning With Reasoning
   Zelikman et al. arXiv 2022.
6. Faith and Fate: Limits of Transformers on Compositionality
   Dziri et al. arXiv 2023.
7. Large Language Models Cannot Self-Correct Reasoning Yet
   Huang et al. arXiv 2023.
8. Language Models are Multilingual Chain-of-Thought Reasoners
   Shi et al. arXiv 2022.
9. Towards Reasoning in Large Language Models: A Survey
   Huang and Chang. arXiv 2022.
10. Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
    Yuan et al. arXiv 2023.

Related reading lists

• Chain-of-Thought & Reasoning
• LLM Agents & Tool-Augmented Language Models
• Scaling Laws and Emergent Capabilities
• Prompt Optimization & In-Context Learning for LLMs
• Quantization for Efficient Inference
• RL from Human Feedback (RLHF)
• Causal Inference & RL
• Data Augmentation for Reinforcement Learning