AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
[Submitted on 1 Oct 2026] Title:World Editing: Intervening on Executable Worlds at Increasing Depth View a PDF of the paper titled World Editing: Intervening on Executable Worlds at Increasing Depth, by Max Ku and Nok-Kan Law and Yu-Chien Tang and Shih-Ying Yeh and Ping Nie and Andy Zheng and Tat Hei Lai and Fei-Yueh Chen and Nikko Yu and Wei-Chieh Sun and Suzy Huang and Chiao-Wei Hsu and Chih-Chuan Huang and Chak-Wing Mak and Ho Yin Sam Ng and Edisy Kin Wai Chan and Min-Hung Chen and Ho Kei Cheng View PDF HTML (experimental) Abstract:Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored. We formulate world editing as intervening on an existing world while preserving properties that should remain unchanged, and introduce intervention depth as an axis describing how strongly an edit couples world entities, dynamics, and systems. We instantiate this capability through industry-grade game modding and introduce IGMWorld, together with IGMBench, a benchmark of 110 tasks and over 1.1K executable state and behavioral criteria across Minecraft and Terraria. The tasks span property, entity, dynamics, and system interventions and are evaluated through deterministic executability, behavioral, preservation, and visual checks. Frontier coding agents already exhibit substantial world-editing capability: the strongest configuration solves 78.2% of tasks under a strict task-level criterion, while criterion-level performance reaches 94.8%. Reliability generally decreases with intervention depth, and this pattern persists even among tasks with similar numbers of evaluation criteria. Most failed edits still build and load successfully, suggesting that the main difficulty is making the edited world behave as requested. Visual consistency remains a separate weakness, with all evaluated configurations below 50% joint visual pass rate. These results show that world editing is a distinct capability from world generation and interaction, and that executable games provide a practical testbed for studying it. Comments: Preprint. Project page: this https URL Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2610.02331 [cs.AI] (or arXiv:2610.02331v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2610.02331 arXiv-issued DOI via DataCite (pending registration) Submission history From: Max W.F. Ku [view email] [v1] Thu, 1 Oct 2026 18:05:47 UTC (1,876 KB) Full-text links: Access Paper: View a PDF of the paper titled World Editing: Intervening on Executable Worlds at Increasing Depth, by Max Ku and Nok-Kan Law and Yu-Chien Tang and Shih-Ying Yeh and Ping Nie and Andy Zheng and Tat Hei Lai and Fei-Yueh Chen and Nikko Yu and Wei-Chieh Sun and Suzy Huang and Chiao-Wei Hsu and Chih-Chuan Huang and Chak-Wing Mak and Ho Yin Sam Ng and Edisy Kin Wai Chan and Min-Hung Chen and Ho Kei Cheng View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI new | recent | 2026-10 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)