LLM-Guided Evolution for Medical Decision Pipelines
Not on the map. Why?
Abstract (arXiv)
Adapting large language models (LLMs) to clinical workflows often requires costly fine-tuning or manual prompt and pipeline engineering. We study LLM-guided MAP-Elites evolution as an inference-time alternative for discovering medical decision strategies and provide an implementation repository at https://github.com/univanxx/llmguidedevomedical. We formulate urgency triage, interactive consultation, and medical image classification as evolutionary searches over executable artifacts optimized by task-specific fitness functions. Across all three settings, evolution improves over manually designed baselines under practical constraints. In triage, evolved programs increase Semigran accuracy from 77.3% to 87.1% and emergency recall from 0.60 to 0.97, while improving safety-weighted held-out MIMIC-ESI performance. In interactive consultation, evolved policies improve the accuracy--cost frontier across Llama-3, Qwen-3.5, and Gemma-4 and transfer to held-out iCRAFTMD. In PneumoniaMNIST, prompt-only evolution improves frozen MedGemma VLMs while preserving strict JSON outputs. Qualitative analysis shows that the gains come from interpretable program-level mechanisms, calibrated triage boundaries, targeted evidence acquisition, selective commitment, and finding-oriented visual decision rules, rather than superficial prompt rewording alone.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 5 Jun 2026.
Builds on
18 of 44 references.
References · 18
- 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
- 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
- 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
- 2015Illuminating search spaces by mapping elitescited by 406
- 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoningcited by 145
- 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
- 2018Automated Machine Learning: From Principles to Practicescited by 62
- 2025ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoningcited by 24
- 2024A Survey of Sustainability in Large Language Models: Applications, Economics, and Challengescited by 18
- 20253MDBench: Medical Multimodal Multi-agent Dialogue Benchmarkcited by 16
- 2025GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithmscited by 11
- 2024Large Language Models as In-context AI Generators for Quality-Diversitycited by 7
6 more
- 2025AutoMedPrompt: A New Framework for Optimizing LLM Medical Prompts Using Textual Gradientscited by 7
- 2024From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuningcited by 5
- 2025EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learningcited by 5
- 2025Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learningcited by 4
- 2025From Pre-labeling to Production: Engineering Lessons from a Machine Learning Pipeline in the Public Sectorcited by 1
- 2026PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosiscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models
- 2025Reasoning LLMs in the Medical Domain: A Literature Survey
- 2025Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
- 2025A Survey of LLM-based Agents in Medicine: How far are we from Baymax?
- 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications
- 2025Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning
- 2024Entry-level guide to the use of large language models for medical research
- 2026Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks