Metraipolis › archive › dc_b6ace91bd4de
ExploreAI: Agentic Exploration Knowledge Bases for Reproducible Observable-Regression Testing of Black-Box VR and 3D Applications — arXiv:2608.21628
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21628
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T08:11:12.227Z
- SHA-256 of the archived text
fd3b59ddefe3fe6c0c861e95e2e3c2d65cd560e10a3feab12a091e9c7a893c6b- Stable URL of this page
https://metraipolis.com/documento/dc_b6ace91bd4de
How to cite
ExploreAI: Agentic Exploration Knowledge Bases for Reproducible Observable-Regression Testing of Black-Box VR and 3D Applications — arXiv:2608.21628 — arXiv (en), https://arxiv.org/abs/2608.21628 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6ace91bd4de (Metraipolis archive dc_b6ace91bd4de, sha256 fd3b59ddefe3fe6c0c861e95e2e3c2d65cd560e10a3feab12a091e9c7a893c6b)
BibTeX
@misc{dcb6ace91bd4de,
title = {ExploreAI: Agentic Exploration Knowledge Bases for Reproducible Observable-Regression Testing of Black-Box VR and 3D Applications — arXiv:2608.21628},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21628},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6ace91bd4de; sha256 fd3b59ddefe3fe6c0c861e95e2e3c2d65cd560e10a3feab12a091e9c7a893c6b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21628. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.SE). Categorie arXiv: Software Engineering (cs.SE) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.21628 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T08:07:32.991Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).