mlsanityData to 7 Oct 2026

PRewrite: Prompt Rewriting with Reinforcement Learning

arXiv 2401.08189 ↗First posted 16 Jan 2024cs.AI cs.CL cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

Prompt engineering is critical for the development of LLM-based applications. However, it is usually done manually in a "trial and error" fashion that can be time consuming, ineffective, and sub-optimal. Even for the prompts which seemingly work well, there is always a lingering question: can the prompts be made better with further modifications? To address these problems, we investigate automated prompt engineering in this paper. Specifically, we propose PRewrite, an automated method to rewrite an under-optimized prompt to a more effective prompt. We instantiate the prompt rewriter using a LLM. The rewriter LLM is trained using reinforcement learning to optimize the performance on a given downstream task. We conduct experiments on diverse benchmark datasets, which demonstrates the effectiveness of PRewrite.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 22 of its 25 references that are in the map. First posted on arXiv 16 Jan 2024.

Builds on

22 of 25 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  9. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  11. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  12. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
10 more
  1. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  2. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  3. 2019How Can We Know What Language Models Know?cited by 953
  4. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  5. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  6. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  7. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  8. 2021BERTese: Learning to Speak to BERTcited by 82
  9. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  10. 2021Efficient (Soft) Q-Learning for Text Generation with Limited Good Datacited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 21; 2026: 12.

43 papers.

Sort:

By area:

  1. 2025A Systematic Survey of Automatic Prompt Optimization Techniquescited by 61
  2. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  3. 2024Prompt Optimization with Human Feedbackcited by 35
  4. 2025How to Train Your Advisor: Steering Black-Box LLMs with Advisor Modelscited by 20
  5. 2025Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Modelscited by 16
  6. 2024QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learningcited by 10
  7. 2025Meta-Prompt Optimization for LLM-Based Sequential Decision Makingcited by 7
  8. 2025Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awarenesscited by 7
  9. 2025Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Modelscited by 6
  10. 2024Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinementcited by 5
  11. 2024Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMscited by 5
  12. 2025Irony Detection, Reasoning and Understanding in Zero-shot Learningcited by 5
31 more
  1. 2024TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domainscited by 4
  2. 2024PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metricscited by 4
  3. 2025How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptationcited by 4
  4. 2025Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogscited by 4
  5. 2024CodeCloak: A Method for Evaluating and Mitigating Code Leakage by LLM Code Assistantscited by 3
  6. 2025A Survey on AgentOps: Categorization, Challenges, and Future Directionscited by 3
  7. 2025FedPOB: Sample-Efficient Federated Prompt Optimization via Banditscited by 3
  8. 2025POET: Preference Optimization for Enhanced Text-to-Image Generationcited by 3
  9. 2026CAP: Controllable Alignment Prompting for Unlearning in LLMscited by 3
  10. 2026Adapting Generalist Robot Policies with Semantic Reinforcement Learningcited by 3
  11. 2024Learning Personalized Prompts for Healthcare Guidancecited by 2
  12. 2026S3-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Datacited by 2
  13. 2024Meta-prompting Optimized Retrieval-augmented Generationcited by 1
  14. 2025Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commercecited by 1
  15. 2025Grammar-Guided Evolutionary Search for Discrete Prompt Optimisationcited by 1
  16. 2025Adaptive Multi-Agent Reasoning via Automated Workflow Generationcited by 1
  17. 2025Instance-level Randomization: Toward More Stable LLM Evaluationscited by 1
  18. 2025Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Modelscited by 1
  19. 2025Beyond Elicitation: Provision-based Prompt Optimization for Knowledge-Intensive Taskscited by 1
  20. 2026VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Modelscited by 1
  21. 2025Prompt reinforcing for long-term planning of large language modelscited by 0
  22. 2025Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Taskscited by 0
  23. 2025CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinementcited by 0
  24. 2026PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactionscited by 0
  25. 2026PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responsescited by 0
  26. 2026Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLMcited by 0
  27. 2026When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scalingcited by 0
  28. 2026Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoningcited by 0
  29. 2026Towards Spec Learning: Inference-Time Alignment from Preference Pairscited by 0
  30. 2026Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilationcited by 0
  31. 2026SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RLcited by 0