Assessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems.
SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
SIGS, Tsinghua University(清华大学信息科学与技术学院);Southern University of Science and Technology(南方科技大学);Guangdong Laboratory of AI and Digital Economy (SZ)(广东人工智能与数字经济实验室);The Hong Kong University of Science and Technology(香港科技大学);Peking University(北京大学)
SCOUT: Semantic scene COverage via Uncertainty-guided Traversal
Nokia Bell Labs, France(诺基亚贝尔实验室,法国);Nokia Bell Labs, Murray Hill, NJ, USA(诺基亚贝尔实验室,美国,新泽西州 Murray Hill);Imperial College London(帝国理工学院伦敦分校);Locus Robotics(Locus机器人技术公司)
LLM-Based Test Case Generation in DBMS through Monte Carlo Tree Search
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Huawei Hong Kong Research Center(华为香港研究中心)
When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception
National University of Singapore(新加坡国立大学);Wuhan University(武汉大学);ByteDance(字节跳动);Nankai University(南开大学);JD Research, JD.com, Inc.(京东研究院(京东有限公司));Zhejiang University(浙江大学);King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);The University of Hong Kong(香港大学)
DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under Occlusion
Jilin University(吉林大学);Shenzhen University(深圳大学);Taiyuan University of Technology(太原理工大学);Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education(符号计算与知识工程教育部重点实验室)
On Mobile Ad Hoc Networks for Coverage of Partially Observable Worlds
McGill University Computer Science Department and MILA Institute(麦吉尔大学计算机科学系和MILA研究所);L2S at the University Paris-Saclay, CentraleSupélec(巴黎萨克雷大学L2S及CentraleSupélec)