Re-Thinking Process Mining in the AI-Based Agents Era
RWTH Aachen University（亚琛工业大学）；Fraunhofer FIT（弗劳恩霍夫应用信息技术研究所）；Higher Institute of Management of Sousse, University of Sousse（苏塞大学苏塞高等管理学院）；Eindhoven University of Technology（埃因霍温理工大学）；Process Insights, ECE Group Services（Process Insights公司（ECE集团服务））；Microsoft（微软公司）
Large Language Models (LLMs) have emerged as powerful conversational interfaces, and their application in process mining (PM) tasks has shown promising results. However, state-of-the-art LLMs struggle with complex scenarios that demand advanced reasoning capabilities. In the literature, two primary approaches have been proposed for implementing PM using LLMs: providing textual insights based on a textual abstraction of the process mining artifact, and generating code executable on the original artifact. This paper proposes utilizing the AI-Based Agents Workflow (AgWf) paradigm to enhance the effectiveness of PM on LLMs. This approach allows for: i) the decomposition of complex tasks into simpler workflows, and ii) the integration of deterministic tools with the domain knowledge of LLMs. We examine various implementations of AgWf and the types of AI-based tasks involved. Additionally, we discuss the CrewAI implementation framework and present examples related to process mining.
Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The University of Melbourne（墨尔本大学）；Zhejiang University（浙江大学）；Ocean University of China（中国海洋大学）；Beijing Jiaotong University（北京交通大学）；Squirrel AI（松鼠AI）；Chongqing University（重庆大学）；University of Electronic Science and Technology of China（电子科技大学）；Hong Kong University of Science and Technology（香港科技大学）
We envision a new era of AI, termed agentic organization, where agents solve complex problems by working collaboratively and concurrently, enabling outcomes beyond individual intelligence. To realize this vision, we introduce asynchronous thinking (AsyncThink) as a new paradigm of reasoning with large language models, which organizes the internal thinking process into concurrently executable structures. Specifically, we propose a thinking protocol where an organizer dynamically assigns sub-queries to workers, merges intermediate knowledge, and produces coherent solutions. More importantly, the…
Advancing Chinese biomedical text mining with community challenges
Sichuan University（四川大学）；West China Hospital（华西医院）；Tongji University（同济大学）；Shanghai Business School（上海商学院）；Takeda Co. Ltd.（武田制药有限公司）；Harbin Institute of Technology（哈尔滨工业大学）
AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining
Jožef Stefan Institute（约瑟夫·斯特凡研究所）；International Postgraduate School Jožef Stefan（约瑟夫·斯特凡国际研究生院）；University of Nova Gorica（新戈里察大学）；Temida d.o.o（Temida有限责任公司）；University of Ljubljana（卢布尔雅那大学）
Automated Analysis Framework for Multilingual Climate-Health Literature Based on Multi-Agent Large Language Model
Tsinghua University（清华大学）；Huawei Technologies Co., Ltd（华为技术有限公司）；Renmin University of China（中国人民大学）；Beijing Forestry University（北京林业大学）；National Institute of Natural Hazards, Ministry of Emergency Management of China（中国应急管理部国家自然灾害防治研究院）
DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era
Massachusetts Institute of Technology（麻省理工学院）；Universidad del Cauca（考卡大学）；University of Michigan（密歇根大学）；Universidad de Chile（智利大学）；São Paulo Federal University（圣保罗联邦大学）；Harvard TH Chan School of Public Health（哈佛陈曾熙公共卫生学院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）
