CPGPrompt: Translating Clinical Guidelines into LLM-Executable Decision Support
Information Science (Health Tech), Cornell Tech, New York, NY, USA（信息科学（健康科技），康奈尔科技，纽约，纽约州）；Systems Engineering, Cornell University, Ithaca, NY, USA（系统工程，康奈尔大学，伊萨卡，纽约州）；Population Health Sciences, Weill Cornell Medicine, New York, NY, USA（人口健康科学，韦尔医学院，纽约，纽约州）；Computer and Information Science, Cornell University, Ithaca, NY, USA（计算机与信息科学，康奈尔大学，伊萨卡，纽约州）；Department of Biomedical Informatics, Columbia University, New York, NY, USA（生物医学信息学系，哥伦比亚大学，纽约，纽约州）；Department of Medicine, Weill Cornell Medicine, New York, NY, USA（医学系，韦尔医学院，纽约，纽约州）；Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA, USA（健康信息管理系，匹兹堡大学，匹兹堡，宾夕法尼亚州）；Clinical and Translational Science Institute, University of Pittsburgh, Pittsburgh, PA, USA（临床与转化科学研究所，匹兹堡大学，匹兹堡，宾夕法尼亚州）；Department of Neurology, UT Southwestern Medical Center, Dallas, TX, USA（神经病学系，德克萨斯西南医学中心，达拉斯，德克萨斯州）；Peter O’Donnell Jr. Brain Institute, UT Southwestern Medical Center, Dallas, TX, USA（彼得·奥·donnell Jr.脑研究所，德克萨斯西南医学中心，达拉斯，德克萨斯州）；Clinical Informatics Center, University of Texas Southwestern Medical Center, Dallas, USA（临床信息学中心，德克萨斯西南医学中心，达拉斯，美国）；Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, New York, NY USA（数字健康人工智能研究所，韦尔医学院，纽约，纽约州）
Ruiqi Deng, Geoffrey Martin, Tony Wang, Gongbo Zhang, Yi Liu, Chunhua Weng, Yanshan Wang, Justin F Rousseau, Yifan Peng
Clinical practice guidelines (CPGs) provide evidence-based recommendations for patient care; however, integrating them into Artificial Intelligence (AI) remains challenging. Previous approaches, such as rule-based systems, face significant limitations, including poor interpretability, inconsistent adherence to guidelines, and narrow domain applicability. To address this, we develop and validate CPGPrompt, an auto-prompting system that converts narrative clinical guidelines into large language models (LLMs).
Our framework translates CPGs into structured decision trees and utilizes an LLM to dynamically navigate them for patient case evaluation. Synthetic vignettes were generated across three domains (headache, lower back pain, and prostate cancer) and distributed into four categories to test different decision scenarios. System performance was assessed on both binary specialty-referral decisions and fine-grained pathway-classification tasks.
The binary specialty referral classification achieved consistently strong performance across all domains (F1: 0.85-1.00), with high recall (1.00 $\pm$ 0.00). In contrast, multi-class pathway assignment showed reduced performance, with domain-specific variations: headache (F1: 0.47), lower back pain (F1: 0.72), and prostate cancer (F1: 0.77). Domain-specific performance differences reflected the structure of each guideline. The headache guideline highlighted challenges with negation handling. The lower back pain guideline required temporal reasoning. In contrast, prostate cancer pathways benefited from quantifiable laboratory tests, resulting in more reliable decision-making.
Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing
Tsinghua University（清华大学）；Wuliangye Yibin Co., Ltd.（五粮液宜宾有限公司）；Yantai University（烟台大学）；Key Laboratory of Digital Construction and Digital Twin, Ministry of Housing and Urban-Rural Development（住房和城乡建设部数字建造与数字孪生重点实验室）
From Natural Language to Executable Option Strategies via Large Language Models
City University of Hong Kong（香港城市大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shanghai University of Finance and Economics（上海财经大学）；University of Science and Technology of China（中国科学技术大学）
Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）；Google Research（谷歌研究院）
We study the problem of translating an image-based, step-by-step assembly manual created by human designers into machine-interpretable instructions. We formulate this problem as a sequential prediction task: at each step, our model reads the manual, locates the components to be added to the current shape, and infers their 3D poses. This task poses the challenge of establishing a 2D-3D correspondence between the manual image and the real 3D object, and 3D pose estimation for unseen 3D objects, since a new component to be added in a step can be an object built from previous steps. To address the…
AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments
Zhongguancun Academy（中关村学院）；University of Science and Technology of China（中国科学技术大学）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Vanke School of Public Health, Tsinghua University（清华大学万科公共卫生学院）
Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns under Structural Constraints
Chalmers University of Technology and University of Gothenburg（楚德大学技术学院和哥德堡大学）
Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning
Idiap Research Institute（Idiap研究 institute）；École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院）；Honda Research Institute Europe（本田欧洲研究院）；Department of Computer Science, University of Manchester（曼彻斯特大学计算机科学系）；National Biomarker Centre, CRUK-MI, University of Manchester（曼彻斯特大学国家生物标记中心）
