The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment
Cardiff School of Technologies, Cardiff Metropolitan University（卡迪夫技术学院，卡迪夫市政大学）；School of Professional Studies, Clark University（专业研究学院，克拉克大学）；Harvard Medical School, Harvard University（哈佛医学院，哈佛大学）
Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks primarily assess textual alignment or task success, less attention has been paid to the structural relationship between linguistic signaling and executable behavior under varying autonomy scaffolds. This study introduces an execution-layer be-havioral measurement approach based on a two-dimensional A-R space defined by Action Rate (A) and Refusal Signal (R), with Divergence (D) capturing coor-dination between the two. Models are evaluated across four normative regimes (Control, Gray, Dilemma, and Malicious) and three autonomy configurations (di-rect execution, planning, and reflection). Rather than assigning aggregate safety scores, the method characterizes how execution and refusal redistribute across contextual framing and scaffold depth. Empirical results show that execution and refusal constitute separable behavioral dimensions whose joint distribution varies systematically across regimes and autonomy levels. Reflection-based scaffolding often shifts configurations toward higher refusal in risk-laden contexts, but redis-tribution patterns differ structurally across models. The A-R representation makes cross-sectional behavioral profiles, scaffold-induced transitions, and coordination variability directly observable. By foregrounding execution-layer characterization over scalar ranking, this work provides a deployment-oriented lens for analyzing and selecting tool-enabled LLM agents in organizational settings where execution privileges and risk tolerance vary.
From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents
National University of Singapore（新加坡国立大学）；University of Toronto（多伦多大学）；University of Minnesota Twin Cities（明尼苏达大学双城分校）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；University of Oxford（牛津大学）
Department of Statistics and Operations Research, UNC-Chapel Hill（统计与运筹学系，北卡罗来纳大学 Chapel Hill 分校）；Imperial College Business School, Imperial College London（帝国理工学院伦敦校区商学院）
Harvard-MIT Health Sciences and Technology（哈佛-麻省理工学院健康科学与技术）；Affective Computing group, MIT Media Lab, Massachusetts Institute of Technology（麻省理工学院媒体实验室情感计算组）
Pain is a subjective experience commonly measured through patient's self report. While there exist numerous situations in which automatic pain estimation methods may be preferred, inter-subject variability in physiological and behavioral pain responses has hindered the development of such methods. In this work, we address this problem by introducing a novel personalized multitask machine learning method for pain estimation based on individual physiological and behavioral pain response profiles, and show its advantages in a dataset containing multimodal responses to nociceptive heat pain.
Workerville: Towards an Organizational Behavior Account of Agent Safety
New York University（纽约大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）；McGill University（麦吉尔大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Relic: From Multi-Agent Collaboration to Persistent Organizational Capability
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Harvey Mudd College（哈维穆德学院）；Yale University（耶鲁大学）；Stanford University（斯坦福大学）；Peking University（北京大学）；National University of Singapore（新加坡国立大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Together AI
PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences)（计算机网络与信息安全部重点实验室，教育部，山东计算机科学中心（济南国家超级计算机中心），齐鲁工业大学（山东省科学院））；University of Chinese Academy of Science（中国科学院大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems
Criminal Psychiatry Research Institute / Sexual Offender Medical Center（犯罪精神病研究机构 / 性犯罪医学中心）；Department of Neuropsychiatry, Kyoto University（神经精神病学系，京都大学）
PEPA: a Persistently Autonomous Embodied Agent with Personalities
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；Shanghai Innovation Institute（上海创新研究院）；School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology（华中科技大学智能制造装备与技术国家重点实验室）
