analiza aiqbench
The paper proposes MedDEx, which has LLMs extract structured patient information while a deterministic rule executor applies guideline logic, and reports better decision accuracy and lower inference cost than multi-step reasoning or multi-agent setups. Its most useful claim for AI readers is that extra LLM reasoning does not reliably improve guideline adherence, which argues for hybrid neuro-symbolic designs in high-stakes domains. The evidence is limited to benchmark experiments, so its generalization to real clinical workflows remains untested.
More Reasoning Is Not Always Better: Executing Clinical Guidelines with LLMs and Rules
arXiv:2610.15912v1 Announce Type: new Abstract: Large language models (LLMs) have shown considerable promise in clinical decision support. However, existing approaches often rely on multi-step reasoning or multi-agent collaboration to execute clinical guidelines, introducing substantial computational overhead without reliably preventing decision errors. To address these limitations, we propose a framework for Medical Decision Execution (MedDEx) that integrates structured patient states with deterministic rule execution to support guideline-based treatment planning. MedDEx separates clinical record interpretation from guideline execution, leveraging LLMs to extract patient information and generate treatment plans while assigning guideline-defined decision logic to a rule executor. Experiments across multiple clinical guideline benchmarks demonstrate that MedDEx improves decision accuracy while reducing inference costs. Further analyses highlight the critical roles of structured patient representations and deterministic rule execution, suggesting that additional LLM reasoning does not necessarily translate into better guideline adherence.
Abstract:Large language models (LLMs) have shown considerable promise in clinical decision support. However, existing approaches often rely on multi-step reasoning or multi-agent collaboration to execute clinical guidelines, introducing substantial computational overhead without reliably preventing decision errors. To address these limitations, we propose a framework for Medical Decision Execution (MedDEx) that integrates structured patient states with deterministic rule execution to support guideline-based treatment planning. MedDEx separates clinical record interpretation from guideline execution, leveraging LLMs to extract patient information and generate treatment plans while assigning guideline-defined decision logic to a rule executor. Experiments across multiple clinical guideline benchmarks demonstrate that MedDEx improves decision accuracy while reducing inference costs. Further analyses highlight the critical roles of structured patient representations and deterministic rule execution, suggesting that additional LLM reasoning does not necessarily translate into better guideline adherence.
Computation and Language (cs.CL)
arXiv:2610.15912 [cs.CL]
(or arXiv:2610.15912v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.15912 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 228 cuvinte
Subiecte conexe
Presentation: The Future of Engineering: Mindsets That Matter When Code Isn’t Enough
InfoQ · 28 iul. 2026
Inside the suddenly explosive world of AI safety
The Verge · 17 sept. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
Informe de riesgos de la IA de frontera (febrero–marzo de 2026)
METR · 19 mai 2026