Tool-augmented LLM systems expose a control regime that learning theory has largely ignored: sequential decision-making with a massive discrete action universe (tools, APIs, documents) in which only a small, unknown subset is relevant for any fixed task distribution. We formalize this setting as Sparse Agentic Control (SAC), where policies admit block-sparse representations over M >> 1 actions and rewards depend on sparse main effects and (optionally) sparse synergies. We study ell_{1,2}-regularized policy learning through a convex surrogate and establish sharp, compressed-sensing-style results: (i) estimation and value suboptimality scale as k (log M / T)^{1/2} under a Policy-RSC condition; (ii) exact tool-support recovery holds via primal-dual witness arguments when T > k log M under incoherence and beta-min; and (iii) any dense policy class requires Omega(M) samples, explaining the instability of prompt-only controllers. We further show that under partial observability, LLMs matter only through a belief/representation error epsilon_b, yielding an additive O(epsilon_b) degradation while preserving logarithmic dependence on M. Extensions cover tuning-free, online, robust, group-sparse, and interaction-aware SAC.
LLMZ+: Contextual Prompt Whitelist Principles for Agentic LLMs
Department of Computer Science Mississippi State University（计算机科学系密苏里州立大学）；Department of Computer Science The University of Alabama（计算机科学系阿拉巴马大学）；Mississippi State University, Mississippi State, MS, USA（密苏里州立大学）；The University of Alabama, Tuscaloosa, AL, USA（阿拉巴马大学）
AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization
Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，地点，国家）；School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）；University of Delaware, Newark, DE, USA（特拉华大学）
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
Sun Yat-sen University（中山大学）；China University of Mining Technology（中国矿业大学）；University of Science and Technology of China（中国科学技术大学）；East China Normal University（华东师范大学）；National University of Singapore（新加坡国立大学）
First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows
School of Enterprise Computing and Digital Transformation（企业计算与数字化转型学院）；Technological University Dublin（都柏林技术大学）；School of Information and Communication Studies（信息与传播研究学院）；University College Dublin（都柏林大学学院）
Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment
Centre for Software Excellence, Huawei Canada（华为加拿大软件卓越中心）；Department of Computer Science, University of Manitoba, Canada（曼尼托巴大学计算机科学系）；School of Computing, Queen’s University, Canada（皇后大学计算科学学院）
UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；Macau University of Science and Technology（澳门科技大学）；School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）；School of Software, Northwestern Polytechnical University（西北工业大学软件学院）；College of Mechanical and Vehicle Engineering, Hunan University（湖南大学机械与运载工程学院）；John von Neumann Faculty of Informatics, Obuda University（欧布达大学约翰·冯·诺依曼信息学院）
LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
Department of Electrical and Computer Engineering, University of California San Diego（加州大学圣迭戈分校电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Alberta（阿尔伯塔大学电气与计算机工程系）
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
University of Oxford（牛津大学）；Shanghai AI Laboratory（上海人工智能实验室）；National University of Singapore（新加坡国立大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Brown University（布朗大学）；University College London（伦敦大学学院）；University of Science and Technology of China（中国科学技术大学）；Imperial College London（伦敦帝国学院）；Dalian University of Technology（大连理工大学）；Chinese Academy of Sciences（中国科学院）；The Chinese University of Hong Kong（香港中文大学）；University of Georgia（佐治亚大学）；University of California, San Diego（加州大学圣地亚哥分校）；University of California, Santa Barbara（加州大学圣塔芭芭拉分校）；University of Bristol（布里斯托大学）
QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Aalto University（阿alto大学）；University of Helsinki（赫尔辛基大学）；University of Liverpool（利物浦大学）；University of Southampton（南安普顿大学）；Technical University of Denmark（丹麦技术大学）
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China（香港科技大学计算机科学与工程系）；School of Law, Tsinghua University, Beijing, China（清华大学法学院）；Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada（滑铁卢大学丘成桐计算机科学系）
How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Electronic Science and Technology of China（电子科技大学）；Nanjing University（南京大学）；Griffith University（格里菲斯大学）；University of New South Wales（新南威尔士大学）
