AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems
School of Mechanical Engineering, Purdue University（普渡大学机械工程学院）；School of Electrical and Computer Engineering, Purdue University（普渡大学电气与计算机工程学院）；Department of Computer Science, Purdue University（普渡大学计算机科学系）；Department of Mathematics, Purdue University（普渡大学数学系）
深度学习模型在正常数据中擅长检测异常模式，但无法直接解决异常分类和跨多样控制系统的可扩展性问题，常难以区分真实故障与噪声或控制系统大暂态响应引起的干扰故障。因此，由于算法故障验证不可扩展，完整的验证与验证（V&V）操作仍由人工在回路（HITL）分析管理，导致不可持续的手动工作量。为自动化此关键监督，我们提出Agent-Integrated Verification and Validation（AIVV），一种混合框架，部署大型语言模型（LLMs）作为决策外层循环。由于严谨的系统验证严格依赖准确的验证，AIVV将数学上标记的异常提升到专门化的LLM委员会。委员会代理通过语义验证干扰和真实故障，基于自然语言（NL）要求确保高保真的系统验证基础。在此基础上，委员会通过评估故障后响应与NL操作容限进行系统验证，最终生成可操作的V&V成果，如增益调谐建议。在无人水下车辆（UUV）时间序列模拟器上的实验表明，AIVV成功将HITL V&V过程数字化，克服了基于规则的故障分类限制，为LLM介导的时序数据领域监督提供了可扩展的蓝图。
英文摘要：
Deep learning models excel at detecting anomaly patterns in normal data. However, they do not provide a direct solution for anomaly classification and scalability across diverse control systems, frequently failing to distinguish genuine faults from nuisance faults caused by noise or the control system's large transient response. Consequently, because algorithmic fault validation remains unscalable, full Verification and Validation (V\&V) operations are still managed by Human-in-the-Loop (HITL) analysis, resulting in an unsustainable manual workload. To automate this essential oversight, we propose Agent-Integrated Verification and Validation (AIVV), a hybrid framework that deploys Large Language Models (LLMs) as a deliberative outer loop. Because rigorous system verification strictly depends on accurate validation, AIVV escalates mathematically flagged anomalies to a role-specialized LLM council. The council agents perform collaborative validation by semantically validating nuisance and true failures based on natural-language (NL) requirements to secure a high-fidelity system-verification baseline. Building on this foundation, the council then performs system verification by assessing post-fault responses against NL operational tolerances, ultimately generating actionable V\&V artifacts, such as gain-tuning proposals. Experiments on a time-series simulator for Unmanned Underwater Vehicles (UUVs) demonstrate that AIVV successfully digitizes the HITL V\&V process, overcoming the limitations of rule-based fault classification and offering a scalable blueprint for LLM-mediated oversight in time-series data domains.
NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models
Department of Computer Science, AI Institute, University of South Carolina（南卡罗来纳大学计算机科学系，人工智能研究所）；Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校计算机科学与电气工程系）；Department of Computer Science and Engineering, The Ohio State University（俄亥俄州立大学计算机科学与工程系）
Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence
University of Macau（澳门大学）；Zhejiang University（浙江大学）；University of Southampton（南安普顿大学）；University of Liverpool（利物浦大学）；Fudan University（复旦大学）；Renmin University of China（中国人民大学）；New York Institute of Technology（纽约理工学院）；University of Bologna（博洛尼亚大学）；Minzu University of China（民族大学）；Hanyang University（汉阳大学）
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Beijing Institute of Technology（北京理工大学）；Zhongguancun Academy（中关村学院）；Xinjiang Future Enterprise Incubator Co., Ltd.（新疆未来企业孵化器有限公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
University of Trento（特伦托大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Sapienza University of Rome（罗马大学）；University of Edinburgh（爱丁堡大学）；Huawei Labs（华为实验室）
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
DISI, University of Trento（特伦托大学DISI学院）；DI, University of Pisa（比萨大学DI学院）；University of Edinburgh（爱丁堡大学）；CIMeC&DISI, University of Trento（特伦托大学CIMeC&DISI学院）
ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming
Hangzhou Institute for Advanced Study, UCAS, Hangzhou, China（杭州高等研究院，UCAS，杭州，中国）；University of Oxford, Oxford, UK（牛津大学，牛津，英国）；University of Science and Technology Beijing, Beijing, China（北京科技大学，北京，中国）；SKLCS and Key Laboratory of System Software, ISCAS, Beijing, China（SKLCS和系统软件重点实验室，ISCAS，北京，中国）；Laboratory of Parallel Software and Computational Science, ISCAS, Beijing, China（并行软件与计算科学实验室，ISCAS，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
NASP-T: A Fuzzy Neuro-Symbolic Transformer for Logic-Constrained Aviation Safety Report Classification
Faculty of Science and Technology (REALTEK)（科学与技术学院）；Norwegian University of Life Sciences (NMBU)（挪威生命科学大学）；Dresden International University (DIU)（德累斯顿国际大学）
ANSR-DT: A Neuro-Symbolic Framework for Adaptive and Explainable Digital Twins
Department of Information Systems, University of Maryland Baltimore County（信息系统系，马里兰大学巴尔的摩县分校）；Department of Computer Science and Engineering, University at Buffalo（计算机科学与工程系，布法罗大学）；Department of Computer Science, University of Colorado Boulder（计算机科学系，科罗拉多大学波德分校）
Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；MBZUAI（马克斯·普朗克人工智能研究所）；McGill University（麦吉尔大学）；The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）；Tsinghua University（清华大学）
Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
University of Oklahoma（俄克拉荷马大学）；Stanford University（斯坦福大学）；School of Electrical and Computer Engineering, Oklahoma State University（电气与计算机工程学院，俄克拉荷马州立大学）；University of Glasgow（格拉斯哥大学）
