发表机构
The University of Arizona; East Carolina University; The University of Texas at San Antonio; Villanova University（亚利桑那大学; 东卡罗来纳大学; 德克萨斯大学圣安东尼奥分校; 维拉诺瓦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ExploreAI是LLM驱动的智能体框架，通过构建探索知识库（EKB），实现黑盒VR与3D应用的可复现可观测回归测试，在多场景中验证了其有效性。
AI 中文摘要
黑盒VR和3D应用的回归测试难度较大，因为可观测的故障取决于测试人员的移动位置、可见对象以及捕获的视图。手动探索测试可以发现此类故障，但其证据复现起来耗时；系统性遍历可复现，但缺乏语义指导，且会将探索预算浪费在低价值视点上。我们观察到，大型语言模型（LLM）能够做出人类测试人员在探索过程中的高层决策：解读任务、选择要检查的对象、对相关对象分组、记录所见内容，以及在证据缺失时决定是否触发再次尝试。基于这一观察，我们提出了ExploreAI，这是一个由LLM驱动的智能体框架，它将重复的感知、导航、多视图捕获执行和日志记录任务交给专门的模块处理，同时使用LLM进行规划、证据记录、捕获策略决策和验证决策。ExploreAI构建了探索知识库（EKB）：这是一种结构化的、针对每次探索运行的对象级记录。对于智能体发现的每个对象，EKB会存储发现该对象的扫描证据、选定的目标、导航路径、多视图捕获内容以及自验证结果。EKB是一种可复用的测试产物，支持在VR或3D应用的不同版本之间进行可复现的可观测回归检查。在Unity、AI2-THOR和BeamNG的6个室内和室外场景中，ExploreAI在完全探索和目标探索两种模式下均构建了高完整性的EKB；LLM模块消融实验显示了语义规划、捕获策略、证据记录和自验证各自的贡献；复现试点进一步表明，与没有EKB上下文的情况相比，EKB引导的轨迹能帮助人类和基于LLM的复现者更有效地复现精确的对象-视图证据。
英文摘要
Black-box VR and 3D applications are difficult to regression test because observable failures depend on where a tester moves, what objects are visible, and which views are captured. Manual exploratory testing can find such failures, but its evidence is time-consuming to reproduce; systematic sweeps are reproducible, but they lack semantic guidance and spend exploration budget on low-value viewpoints. We observe that an LLM can make the high-level decisions a human tester makes during exploration: interpreting a task, choosing which objects to inspect, grouping related objects, recording what it saw, and deciding when missing evidence should trigger another attempt. Based on this observation, we present ExploreAI, an LLM-driven agentic framework that offloads repeated perception, navigation, multi-view capture execution, and logging to specialized modules while using the LLM for planning, evidence recording, capture-policy decisions, and verification decisions. ExploreAI constructs an Exploration Knowledge Base (EKB): a structured, per-object record of one exploration run. For each object the agent finds, the EKB stores the scan evidence that exposed it, the selected target, the navigation path, the multi-view capture, and the self-verification result. The EKB is a reusable testing artifact that supports reproducible observable-regression checking across versions of a VR or 3D application. Across six indoor and outdoor scenes in Unity, AI2-THOR, and BeamNG, ExploreAI constructs high-completeness EKBs under both complete and target exploration, and an LLM-module ablation shows where semantic planning, capture policy, evidence recording, and self-verification contribute. Reproduction pilots further show that EKB-guided traces help both humans and LLM-based reproducers reproduce exact object-view evidence more effectively than conditions without EKB context.
Comments11 pages, 3 figures, 8 tables
