Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these deficits. In this work, we propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA), a supervision-free framework that bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs. SPECTRA enforces Soft Structured Multi-turn Rollouts, a topological constraint that directs agents to explicitly sequence tool derived evidence before synthesis, effectively grounding reasoning in visual observations. We employ a multi-objective reward signal that simultaneously maximizes task correctness, rollout structure, and tool utility, enabling agent to self-discover robust behaviors without human preference labels. We further introduce Tool Instrumental Utility (TIU), a novel metric to quantify tool efficacy in the absence of ground truth. Extensive evaluations across composite and out-of-distribution (MMMU-Pro) benchmarks demonstrate that SPECTRA boosts agentic trajectories, improving task accuracy by up to 5% and tool efficiency by 9%, enabling more efficient multimodal agents that learn effectively from environmental interaction alone.
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
CARDS (Center for Real-Time Distributed Sensing and Autonomy), University of Maryland Baltimore County, Baltimore, MD, USA（实时分布式传感与自主性中心，马里兰大学巴尔的摩县）；Massachusetts Institute of Technology, Cambridge, MA, USA（麻省理工学院）
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Meituan（美团）；MBZUAI（Mohamed bin Zayed University of Artificial Intelligence）；Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）
EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis
School of Biological Science and Medical Engineering, Southeast University（东南大学生物科学与医学工程学院）；Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University（江苏省生物材料与器件重点实验室）；State Key Laboratory of Digital Medical Engineering, Southeast University（国家数字医学工程重点实验室）；The First Affiliated Hospital of Nanjing Medical University（南京医科大学第一附属医院）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing（江苏省联合国际医学信息处理联合实验室）；Laboratory of Image Science and Technology, the School of Computer Science and Engineering, Southeast University（图像科学与技术实验室，东南大学计算机科学与工程学院）
Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine
ARIA Lab, Signal Processing Systems, Department of Electrical Engineering, Eindhoven University of Technology（ARIA实验室，信号处理系统，电气工程系，埃因霍温理工大学）；Laboratory of Chemical Biology, Department of Biomedical Engineering, Eindhoven University of Technology（化学生物学实验室，生物医学工程系，埃因霍温理工大学）；The Louis Family Laboratory for Targeted Drug Delivery and Personalized Medicine Technologies, Department of Chemical Engineering, Technion - Israel Institute of Technology（定向药物输送与个性化医学技术实验室，化学工程系，技术离子-以色列理工学院）；Department of Nanomedicine and Theranostics, Institute for Experimental Molecular Imaging (ExMI), RWTH Aachen University Hospital（纳米医学与诊疗学系，实验分子成像研究所（ExMI），亚琛工业大学医院）；Department of Internal Medicine and Radboud Center for Infectious Diseases (RCI), Radboud University Medical Center（内科学系和Radboud感染疾病中心（RCI），Radboud大学医学中心）
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
State Key Laboratory of Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学）；School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学）；School of Intelligence Science and Technology, Nanjing University, China（智能科学与技术学院，南京大学）；Centre for Frontier AI Research（前沿人工智能研究中心）；Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，新加坡科技研究局）；Department of Computer Science and Engineering, Hong Kong University of Science and Technology, China（香港科学与技术大学计算机科学与工程系）
