Prompt Optimization & In-Context Learning for LLMs Reading List

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

Prompting turns frozen language models into adaptable systems. This list follows the arc from few-shot in-context learning and continuous prompt tuning to modern automatic optimizers that search, evolve, and compile prompts for reliable LLM behavior.

Prompt Optimization & In-Context Learning for LLMs: 10 key papers

1. Large Language Models Are Human-Level Prompt Engineers
   Zhou et al. arXiv 2022.
2. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
   Shin et al. arXiv 2020.
3. The Power of Scale for Parameter-Efficient Prompt Tuning
   Lester et al. arXiv 2021.
4. Prefix-Tuning: Optimizing Continuous Prompts for Generation
   Li and Liang. arXiv 2021.
5. GPT Understands, Too
   Liu et al. arXiv 2021.
6. Making Pre-trained Language Models Better Few-shot Learners
   Gao et al. arXiv 2020.
7. Black-box Prompt Learning for Pre-trained Language Models
   Diao et al. arXiv 2022.
8. Large Language Models as Optimizers
   Yang et al. arXiv 2023.
9. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
   Fernando et al. arXiv 2023.
10. Automatic Prompt Optimization with "Gradient Descent" and Beam Search
    Pryzant et al. arXiv 2023.

Related reading lists

• In-Context RL & Prompting
• Chain-of-Thought & Reasoning
• Reasoning in LLMs
• LLM Agents & Tool-Augmented Language Models
• Quantization for Efficient Inference
• Vision-Language Models & Multimodal Learning
• Few-Shot RL & Meta-Learning
• Instruction Following & Finetuning