الملخص
Autonomous agents have made rapid progress in general-purpose computer use, but reliable automation of professional industrial engineering remains out of reach, as engineering workflows demand reasoning over geometric and physical constraints and dependencies preserved across software and design stages. We present EngiWorld, the first benchmark structured around the complete design loop: 1,301 expert-curated tasks spanning 6 engineering domains (CAD, CAE, CAM, BIM, EDA, and 3D visualization) and 26 professional software platforms, with both GUI and CLI interfaces and 6 task types ranging from software-selection to open-ended tasks. We further introduce an artifact-centric evaluation methodology built on a unified domain-verifier suite, which programmatically checks the geometric validity, physical feasibility, and rule compliance of final and intermediate artifacts, and scores quantitative design tasks continuously by specification attainment rather than binary success. Evaluation of seven frontier models reveals a substantial capability gap: the strongest model achieves an EngiScore of only 44.3, and just 3.6% of multi-software attempts succeed. EngiWorld provides the first rigorous foundation for measuring progress toward agents that operate professional engineering software end to end.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Gao, H., Qu, H., Lei, Y., Sun, H., Li, H., Wei, Y., Xue, N., Yu, X., Tao, Z., Zang, Y., Wang, Y., Tang, J., Li, Y., Zhou, J., Luo, J., Zeng, B., Shen, C., Jiang, H., Chen, C., Qu, B., Huang, O., & Wang, Z. (2026). EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? https://omanscience.com/ar/articles/engiworld-what-can-frontier-agents-deliver-in-professional-engineering-environments
MLA 9
Gao, Hongcheng, et al. "EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?" https://omanscience.com/ar/articles/engiworld-what-can-frontier-agents-deliver-in-professional-engineering-environments.
شيكاغو (المؤلف–التاريخ)
Gao, Hongcheng, Hailong Qu, Yu Lei, Henghui Sun, Haoyang Li, Yipeng Wei, Naihao Xue, Xiaohan Yu, Zhuo Tao, Yihe Zang, Yajiao Wang, Jingyi Tang, Yi Li, Jingjing Zhou, Jie Luo, Bohan Zeng, Chengyu Shen, Hao Jiang, Chong Chen, Bowen Qu, Olive Huang, and Zeqiang Wang. 2026. "EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?" https://omanscience.com/ar/articles/engiworld-what-can-frontier-agents-deliver-in-professional-engineering-environments.
هارفارد
Gao, H., Qu, H., Lei, Y., Sun, H., Li, H., Wei, Y., Xue, N., Yu, X., Tao, Z., Zang, Y., Wang, Y., Tang, J., Li, Y., Zhou, J., Luo, J., Zeng, B., Shen, C., Jiang, H., Chen, C., Qu, B., Huang, O. and Wang, Z. (2026) 'EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?', Available at: https://omanscience.com/ar/articles/engiworld-what-can-frontier-agents-deliver-in-professional-engineering-environments.
فانكوفر
Gao H, Qu H, Lei Y, Sun H, Li H, Wei Y, et al. EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? https://omanscience.com/ar/articles/engiworld-what-can-frontier-agents-deliver-in-professional-engineering-environments
IEEE
H. Gao, H. Qu, Y. Lei, H. Sun, H. Li, Y. Wei, N. Xue, X. Yu, Z. Tao, Y. Zang, Y. Wang, J. Tang, Y. Li, J. Zhou, J. Luo, B. Zeng, C. Shen, H. Jiang, C. Chen, B. Qu, O. Huang, and Z. Wang, "EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?," https://omanscience.com/ar/articles/engiworld-what-can-frontier-agents-deliver-in-professional-engineering-environments.