mlsanityData to 14 Oct 2026

PRL: Prompts from Reinforcement Learning

arXiv 2505.14412 ↗First posted 20 May 2025cs.AI cs.CLcited by 9

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting them typically demands expert intuition and a nuanced understanding of the task. Moreover, the most impactful prompts often hinge on subtle semantic cues, ones that may elude human perception but are crucial for guiding LLM behavior. In this paper, we introduce PRL (Prompts from Reinforcement Learning), a novel RL-based approach for automatic prompt generation. Unlike previous methods, PRL can produce novel few-shot examples that were not seen during training. Our approach achieves state-of-the-art performance across a range of benchmarks, including text classification, simplification, and summarization. On the classification task, it surpasses prior methods by 2.58% over APE and 1.00% over EvoPrompt. Additionally, it improves the average ROUGE scores on the summarization task by 4.32 over APE and by 2.12 over EvoPrompt and the SARI score on simplification by 6.93 over APE and by 6.01 over EvoPrompt. Our code is available at https://github.com/Batorskq/prl .

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 41 of its 71 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

41 of 71 references.

References · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  11. 2023Let's Verify Step by Stepcited by 3,789
  12. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
29 more
  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  3. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  4. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  7. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  8. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  10. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  11. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  12. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  13. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  14. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  15. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 535
  16. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
  17. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  18. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 355
  19. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
  20. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Promptscited by 226
  21. 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 149
  22. 2020ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformationscited by 101
  23. 2024What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineeringcited by 90
  24. 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representationscited by 82
  25. 2023Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injectioncited by 59
  26. 2024POSIX: A Prompt Sensitivity Index For Large Language Modelscited by 59
  27. 2024Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Togethercited by 40
  28. 2025Benchmarking Prompt Sensitivity in Large Language Modelscited by 38
  29. 2024CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptationcited by 4
  2. 2025GPS: General Per-Sample Promptercited by 3
  3. 2026Adapting Generalist Robot Policies with Semantic Reinforcement Learningcited by 3
  4. 2025PIAST: Rapid Prompting with In-context Augmentation for Scarce Training datacited by 2
  5. 2026TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregationcited by 1
  6. 2025WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learningcited by 0
  7. 2026ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion modelscited by 0
  8. 2026GFlowPO: Generative Flow Network as a Language Model Prompt Optimizercited by 0
  9. 2026Learning Evidence Highlighting for Frozen LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RLPE: Teaching LLMs to Prompt with Reinforcement Learning
  2. 2024GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning
  3. 2024PRewrite: Prompt Rewriting with Reinforcement Learning
  4. 2025Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
  5. 2025Prompt Curriculum Learning for Efficient LLM Post-Training
  6. 2025AutoPDL: Automatic Prompt Optimization for LLM Agents
  7. 2026TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter
  8. 2026Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience