Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on prompt engineering of a single agent, making it difficult to observe or compare how models handle uncertainty and coordination across interconnected decision stages and with human oversight. We introduce a multi-agent system formalized as a finite-horizon Markov Decision Process (MDP) with a directed acyclic structure. Each agent corresponds to a specific role or decision stage (e.g., content, business, or legal review in a compliance workflow), with predefined transitions representing task escalation or completion. Epistemic uncertainty is quantified at the agent level using Monte Carlo estimation, while system-level uncertainty is captured by the MDP's termination in either an automated labeled state or a human-review state. We illustrate the approach through a case study in AI safety evaluation for self-harm detection, implemented as a multi-agent compliance system. Results demonstrate improvements over a single-agent baseline, including up to a 19\% increase in accuracy, up to an 85x reduction in required human review, and, in some configurations, reduced processing time.
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach
Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
Department of Civil and Environmental Engineering, University of Houston（土木与环境工程系，休斯顿大学）；Center for Transportation Research, The University of Texas at Austin（交通研究中心，德克萨斯大学奥斯汀分校）；Department of Information Science Technology, University of Houston（信息科学与技术系，休斯顿大学）
Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization
1 Department of Computer Science, University of Chicago；2 Data Science \& Learning Division, Argonne National Laboratory；3 Department of Civil, Materials；Environmental Engineering, University of Illinois at Chicago
Snakemaker: Seamlessly transforming ad-hoc analyses into sustainable Snakemake workflows with generative AI
Dipartimento di Scienze della Vita e Biologia dei Sistemi and MBC, Università di Torino（托里尼大学生命科学与系统生物学系及MBC）；Algorithms for reproducible bioinformatics, Genome Informatics, Institute of Human Genetics, University Hospital Essen, University of Duisburg-Essen（杜伊斯堡-埃森大学生物信息学算法、基因组信息学、人类遗传学研究所、埃森大学医院）
Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models
Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；Mount Sinai Hospital（西奈山医院）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Pittsburgh School of Medicine（匹兹堡大学医学院）
KC-GenRe: A Knowledge-constrained Generative Re-ranking Method Based on Large Language Models for Knowledge Graph Completion
Defense Innovation Institute, Academy of Military Sciences（军事科学院国防创新研究院）；Information Research Center of Military Science（军事科学信息研究中心）；National Key Laboratory of Parallel and Distributed Computing（并行与分布计算国家重点实验室）
Simulating Generative Social Agents via Theory-Informed Workflow Design
Information Hub The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）信息中心）；Department of Electronic Engineering Tsinghua University（清华大学电子工程系）
Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks
Barcelona Supercomputing Center (BSC)（巴塞罗那超级计算中心（BSC））；Nostrum Biodiscovery S.L.（诺斯特伦生物发现有限公司）；RA Capital（RA资本）；Superluminal Medicines（超光速药物公司）；ICREA（加泰罗尼亚研究与高级研究所）；Dimensional Consulting（三维咨询公司）
Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding
School of Cyber Science and Engineering, Wuhan University（武汉大学网络科学与工程学院）；Beijing Rigour Technology Co., Ltd.（北京睿格科技有限公司）；School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学网络空间学院）；North China Power Engineering Co., Ltd. of China Power Engineering Consulting Group（中国电力工程顾问集团华北电力工程有限公司）
Preparing to Integrate Generative Pretrained Transformer Series 4 models into Genetic Variant Assessment Workflows: Assessing Performance, Drift, and Nondeterminism Characteristics Relative to Classifying Functional Evidence in Literature
Mass General Brigham Personalized Medicine（麻省总医院布里格姆个性化医学）；Brigham and Women’s Hospital（布莱根妇女医院）；Microsoft Corporation（微软公司）
