mlsanityData to 7 Oct 2026

Prompt Engineering Through the Lens of Optimal Control

arXiv 2310.14201 ↗First posted 22 Oct 2023cs.LG math.OCcited by 16

Not on the map. Why?

Abstract (arXiv)

Prompt Engineering (PE) has emerged as a critical technique for guiding Large Language Models (LLMs) in solving intricate tasks. Its importance is highlighted by its potential to significantly enhance the efficiency and effectiveness of human-machine interaction. As tasks grow increasingly complex, recent advanced PE methods have extended beyond the limitations of single-round interactions to embrace multi-round interactions, which allows for a deeper and more nuanced engagement with LLMs. In this paper, we propose an optimal control framework tailored for multi-round interactions with LLMs. This framework provides a unified mathematical structure that not only systematizes the existing PE methods but also sets the stage for rigorous analytical improvements. Furthermore, we extend this framework to include PE via ensemble methods and multi-agent collaboration, thereby enlarging the scope of applicability. By adopting an optimal control perspective, we offer fresh insights into existing PE methods and highlight theoretical challenges that warrant future research. Besides, our work lays a foundation for the development of more effective and interpretable PE methods.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 33 of its 48 references that are in the map. First posted on arXiv 22 Oct 2023.

Builds on

33 of 48 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  10. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  11. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  12. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
21 more
  1. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  2. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  3. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  4. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  5. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  6. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 293
  7. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  8. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  9. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  10. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  11. 2022Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizerscited by 204
  12. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  13. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  14. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  15. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  16. 2020AraGPT2: Pre-Trained Transformer for Arabic Language Generationcited by 54
  17. 2023What's the Magic Word? A Control Theory of LLM Promptingcited by 41
  18. 2019Growing Action Spacescited by 29
  19. 2023Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineeringcited by 17
  20. 2023Prompt Space Optimizing Few-shot Reasoning Success with Large Language Modelscited by 11
  21. 2023Hint of Pseudo Code (HoPC): Zero-Shot Step by Step Pseudo Code Reasoning Promptingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 8; 2026: 4.

16 papers.

Sort:

By area:

  1. 2024Aligning Large Language Models with Representation Editing: A Control Perspectivecited by 62
  2. 2024LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Modelcited by 43
  3. 2024LiSeCo: Linear Semantic Control for Language Generationcited by 20
  4. 2025Activation Steering with a Feedback Controllercited by 11
  5. 2024Anchor function: a type of benchmark functions for studying language modelscited by 10
  6. 2025Preemptive Detection and Steering of LLM Misalignment via Latent Reachabilitycited by 10
  7. 2026Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Controlcited by 8
  8. 2025A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Modelscited by 4
  9. 2025Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMscited by 3
  10. 2025CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosiscited by 2
  11. 2025A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minimacited by 2
  12. 2025Decentralized Multi-Agent Goal Assignment for Path Planning using Large Language Modelscited by 1
4 more
  1. 2026Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equationscited by 1
  2. 2026When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Modelscited by 1
  3. 2026Training-Free Universal Approximation by Prompting Random Transformerscited by 1
  4. 2025Dual Filter: A Transformer-like Inference Architecture for Hidden Markov Modelscited by 0