mlsanityData to 7 Oct 2026

A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models

arXiv 2501.03508 ↗First posted 7 Jan 2025cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Designing effective prompts is essential to guiding large language models (LLMs) toward desired responses. Automated prompt engineering aims to reduce reliance on manual effort by streamlining the design, refinement, and optimization of natural language prompts. This paper proposes an optimal learning framework for automated prompt engineering, designed to sequentially identify effective prompt features while efficiently allocating a limited evaluation budget. We introduce a feature-based method to express prompts, which significantly broadens the search space. Bayesian regression is employed to utilize correlations among similar prompts, accelerating the learning process. To efficiently explore the large space of prompt features for a high quality prompt, we adopt the forward-looking Knowledge-Gradient (KG) policy for sequential optimal learning. The KG policy is computed efficiently by solving mixed-integer second-order cone optimization problems, making it scalable and capable of accommodating prompts characterized only through constraints. We demonstrate that our method significantly outperforms a set of benchmark strategies assessed on instruction induction tasks. The results highlight the advantages of using the KG policy for prompt learning given a limited evaluation budget. Our framework provides a solution to deploying automated prompt engineering in a wider range applications where prompt evaluation is costly.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 7 Jan 2025.

Builds on

16 of 35 references.

References · 16

  1. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  2. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  3. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  4. 2022A Survey on In-context Learningcited by 717
  5. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  6. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  7. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  8. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 220
  9. 2022Instruction Induction: From Few Examples to Natural Language Task Descriptionscited by 152
  10. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 143
  11. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  12. 2023Large Language Models are Diverse Role-Players for Summarization Evaluationcited by 62
4 more
  1. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 29
  2. 2024APEER: Automatic Prompt Engineering Enhances Large Language Model Rerankingcited by 28
  3. 2023Prompt Engineering Through the Lens of Optimal Controlcited by 16
  4. 2024In-Context Example Ordering Guided by Label Distributionscited by 12

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedbackcited by 7
  2. 2025Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systemscited by 6
  3. 2025Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogscited by 4
  4. 2025CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Predictioncited by 1