EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for clinical treatment and surgery
Abstract (arXiv)
Prompt engineering significantly influences the reliability and clinical utility of Large Language Models (LLMs) in medical applications. Current optimization approaches inadequately address domain-specific medical knowledge and safety requirements. This paper introduces EMPOWER, a novel evolutionary framework that enhances medical prompt quality through specialized representation learning, multi-dimensional evaluation, and structure-preserving algorithms. Our methodology incorporates: (1) a medical terminology attention mechanism, (2) a comprehensive assessment architecture evaluating clarity, specificity, clinical relevance, and factual accuracy, (3) a component-level evolutionary algorithm preserving clinical reasoning integrity, and (4) a semantic verification module ensuring adherence to medical knowledge. Evaluation across diagnostic, therapeutic, and educational tasks demonstrates significant improvements: 24.7% reduction in factually incorrect content, 19.6% enhancement in domain specificity, and 15.3% higher clinician preference in blinded evaluations. The framework addresses critical challenges in developing clinically appropriate prompts, facilitating more responsible integration of LLMs into healthcare settings.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in RL for clinical treatment and surgery, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 25 Aug 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Citing papers per year: 2025: 1; 2026: 5.
6 papers.
- 2026What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generationcited by 8
- 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Modelcited by 7
- 2026IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Toolscited by 2
- 2026LLM-Guided Evolution for Medical Decision Pipelinescited by 0
- 2026Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Expertscited by 0
- 2026X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoningcited by 0
- 2026X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning12 Oct 2026
- 2026Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts14 Jun 2026
- 2026LLM-Guided Evolution for Medical Decision Pipelines5 Jun 2026
- 2026IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools20 May 2026
- 2026What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation12 Feb 2026
- 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model25 Nov 2025
Similar, not cited
Close in wording, no citation either way
- 2025Reasoning LLMs in the Medical Domain: A Literature Survey
- 2025AutoMedPrompt: A New Framework for Optimizing LLM Medical Prompts Using Textual Gradients
- 2023An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing
- 2026Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models
- 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications
- 2026MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment
- 2025Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning
- 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs