Develop AI Agents for System Engineering in Factorio
Not on the map. Why?
Abstract (arXiv)
Continuing advances in frontier model research are paving the way for widespread deployment of AI agents. Meanwhile, global interest in building large, complex systems in software, manufacturing, energy and logistics has never been greater. Although AI driven system engineering holds tremendous promise, the static benchmarks dominating agent evaluations today fail to capture the crucial skills required for implementing dynamic systems, such as managing uncertain trade-offs and ensuring proactive adaptability. This position paper advocates for training and evaluating AI agents' system engineering abilities through automation-oriented sandbox games-particularly Factorio. By directing research efforts in this direction, we can equip AI agents with the specialized reasoning and long-horizon planning necessary to design, maintain, and optimize tomorrow's most demanding engineering projects.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 7 of its 52 references that are in the map. First posted on arXiv 3 Feb 2025.
Builds on
7 of 52 references.
References · 7
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
- 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
- 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 203
- 2023A Tutorial on Meta-Reinforcement Learningcited by 108
Built on by
Citing papers per year: 2025: 1.
1 paper.