Despite achieving remarkable success in complex tasks, Deep Reinforcement Learning (DRL) is still suffering from critical issues in practical applications, such as low data efficiency, lack of interpretability, and limited cross-environment transferability. However, the learned policy generating actions based on states are sensitive to the environmental changes, struggling to guarantee behavioral safety and compliance. Recent research shows that integrating Large Language Models (LLMs) with symbolic planning is promising in addressing these challenges. Inspired by this, we introduce a novel LLM-driven closed-loop framework, which enables semantic-driven skill reuse and real-time constraint monitoring by mapping natural language instructions into executable rules and semantically annotating automatically created options. The proposed approach utilizes the general knowledge of LLMs to facilitate exploration efficiency and adapt to transferable options for similar environments, and provides inherent interpretability through semantic annotations. To validate the effectiveness of this framework, we conduct experiments on two domains, Office World and Montezuma's Revenge, respectively. The results demonstrate superior performance in data efficiency, constraint compliance, and cross-task transferability.
Dynamic Decision Frequency with Continuous Options
Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）；Department of Computer Science, University of Alberta（阿尔伯塔大学计算机科学系）；Department of Computer Science and Digital Science Center, University of Innsbruck（因斯布鲁克大学计算机科学系和数字科学中心）
Facilitating automated conversion of scientific knowledge into scientific simulation models with the Machine Assisted Generation, Calibration, and Comparison (MAGCC) Framework
University of Vermont Larner College of Medicine（佛蒙特大学拉纳医学院）
TreeWriter: AI-Assisted Hierarchical Planning and Writing for Long-Form Documents
Department of Computer Science, University of Toronto, Sandford Fleming Building, 10 King’s College Road, ON M5S 3G4, Toronto, Canada；Vector Institute for Artificial Intelligence, 661 University Ave. Suite 710, ON M5G 1M1, Toronto, Canada；Department of Chemistry, University of Toronto, Lash Miller Chemical Laboratories, 80 St. George Street, ON M5S 3H6, Toronto, Canada；Department of Mathematical；Computational Sciences, University of Toronto Mississauga, 3359 Mississauga Road, Deerfield Hall, ON L5L 1C6, Mississauga, Canada；Department of Materials Science \& Engineering, University of Toronto, 184 College St., M5S 3E4, Toronto, Canada；Department of Chemical Engineering \& Applied Chemistry, University of Toronto, 200 College St. ON M5S 3E5, Toronto, Canada；Acceleration Consortium, 700 University Ave., M7A 2S4, Toronto, Canada；Canadian Institute for Advanced Research (CIFAR), 661 University Ave., M5G 1M1, Toronto, Canada；NVIDIA, 431 King St W \#6th, M5V 1K4, Toronto, Canada
Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty
School of Computing（计算学院）；Information Systems, Faculty of Engineering（信息学院，工程学院）；Information Technology, The University of Melbourne, Parkville VIC 3010, Australia（信息科技，墨尔本大学，帕克维尔 VIC 3010, 澳大利亚）；Industrial Research Organization (CSIRO), Research Way, Clayton VIC 3168, Australia（工业研究组织（CSIRO），Research Way，克莱顿 VIC 3168, 澳大利亚）；Department of Psychiatry, The University of Melbourne, Parkville VIC 3010, Australia（精神病学系，墨尔本大学，帕克维尔 VIC 3010, 澳大利亚）
From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
Department of Computer Science, The University of Alabama（阿拉巴马大学计算机科学系）；The University of Alabama（阿拉巴马大学）；Alabama Water Institute, The University of Alabama（阿拉巴马水研究院，阿拉巴马大学）
LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai AI Laboratory（上海人工智能实验室）；SenseTime Group Limited（商汤科技集团有限公司）；Nokia Bell Labs（诺基亚贝尔实验室）；The University of Hong Kong（香港大学）
