arXiv cs.AI· Fuqiang Wang, Zheng Guo, Xiaoming Wu, Hanlin Kong, Nayu Liu, Chuanting Zhang, Daojun Liang, Jingxuan Wei·· 6 天前AI 评分25
VIGOR：面向场景程序的工业几何优化与修复，实现可验证的工程可行性
VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
AI 导读
针对 LLM 生成的工业场景程序"可执行但工程不可行"的问题，研究者构建了含 1,749 个可构建场景、每个场景 94 项最终状态几何检查的数据集，并提出 VIGOR，将监督式场景程序生成与执行验证、分阶段几何精修结合。VIGOR 达到 96.86% Complete Feasibility 和 91.20 的 Overall 分数，Overall 较最强基线高出 10.42 分。
正文 · 原文
Abstract:Large language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-language instructions. However, executability does not imply engineering feasibility: an industrial scene program may execute successfully while its final state still violates coupled boundary, collision, clearance, aisle, or structural constraints. We identify this mismatch as the executability-engineering-feasibility gap, where locally plausible placements can remain globally infeasible because corrections to one device may introduce violations elsewhere. To make this gap measurable in a controlled setting, we construct an execution-grounded industrial scene-program dataset with 1,749 constructible scenarios, complete executable programs, and 94 final-state geometric checks per scenario. We further propose VIGOR, which combines supervised scene-program generation with execution-grounded verification and staged geometric refinement. Supervised fine-tuning establishes complete program generation, local projection resolves independently correctable violations, and joint conflict-graph repair coordinates residual multi-object conflicts while preserving structural relations. Experiments show that VIGOR achieves 96.86% Complete Feasibility and an Overall score of 91.20, outperforming the strongest evaluated baseline by 10.42 points in Overall. These results show that, under controlled industrial layout conditions, reliable scene-program generation requires not only executable programs, but also explicit verification and coordinated resolution of coupled engineering constraints.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.13145 [cs.AI] |
| (or arXiv:2610.13145v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13145 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zheng Guo [view email]
[v1]
Fri, 9 Oct 2026 07:34:19 UTC (8,840 KB)
来源：arXiv cs.AI · arxiv.org