analiza aiqbench
This paper presents CRAFT-AI, an agentic system that leverages natural language processing and Asset Administration Shells to automate the generation of flexible manufacturing configurations from user requirements. The study demonstrates the feasibility of using tool-using AI agents to interpret production needs, match engineering knowledge, and generate valid factory scenes while providing specific feedback on domain gaps or incompatible component selections. By bridging high-level intent with low-level system implementation, this work advances the application of generative AI in industrial automation and resilient infrastructure design.
CRAFT-AI: Capability and Requirement Alignment for Flexible Manufacturing through Agentic AI
De la arXiv
Text integralarXiv:2611.12092v1 Announce Type: new Abstract: One of the fundamental needs for reaching resilient production infrastructure is flexible manufacturing, which requires translating changing production requirements into implementable system configurations. This paper introduces \textbf{CRAFT-AI}, an agentic AI approach combining natural language (NL) requirement interpretation, Asset Administration Shell (AAS)-based capability descriptions, and reusable engineering knowledge from existing manufacturing configurations. A tool-using AI agent matches requirements with available capabilities and reference implementations to generate manufacturing scenes and corresponding AAS instances.
The approach is demonstrated using a Factory I/O prototype with twelve reference scenes and five illustrative manufacturing tasks of varying complexity, providing an initial feasibility assessment of the proposed AAS-enabled, system-level generative engineering approach. For the four valid user task descriptions, proper requirements, correct references to the relevant engineering knowledge, correct components and lastly a valid Factory I/O scene are generated. For the task with missing engineering knowledge and a wrong sensor selection, the user is informed about which requirements of the scene generation lack domain knowledge and also which sensor is not compatible with the selected raw material by the user with link to the related documentation. After fixing the task description, the correct scene is seamlessly generated. \textbf{CRAFT-AI} highlights the importance of safeguards for risk perception and communication in foundation model-driven solutions.
Abstract:One of the fundamental needs for reaching resilient production infrastructure is flexible manufacturing, which requires translating changing production requirements into implementable system configurations. This paper introduces \textbf{CRAFT-AI}, an agentic AI approach combining natural language (NL) requirement interpretation, Asset Administration Shell (AAS)-based capability descriptions, and reusable engineering knowledge from existing manufacturing configurations. A tool-using AI agent matches requirements with available capabilities and reference implementations to generate manufacturing scenes and corresponding AAS instances.
The approach is demonstrated using a Factory I/O prototype with twelve reference scenes and five illustrative manufacturing tasks of varying complexity, providing an initial feasibility assessment of the proposed AAS-enabled, system-level generative engineering approach. For the four valid user task descriptions, proper requirements, correct references to the relevant engineering knowledge, correct components and lastly a valid Factory I/O scene are generated. For the task with missing engineering knowledge and a wrong sensor selection, the user is informed about which requirements of the scene generation lack domain knowledge and also which sensor is not compatible with the selected raw material by the user with link to the related documentation. After fixing the task description, the correct scene is seamlessly generated. \textbf{CRAFT-AI} highlights the importance of safeguards for risk perception and communication in foundation model-driven solutions.
Artificial Intelligence (cs.AI)
arXiv:2611.12092 [cs.AI]
(or arXiv:2611.12092v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2611.12092 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Text integral sub licența deschisă a publicației · 299 cuvinte
Subiecte conexe

EV Group Helps Accelerate Qubit Scaling for Quantum Computing Through Advanced Packaging Expertise
The Quantum Insider · 9 nov. 2026

EV Group Applies Advanced Packaging Expertise to Quantum Chip Development
HPCwire · 9 nov. 2026

SBA, Pentagon Partner to Strengthen Defense Manufacturing
military.com · 23 oct. 2026

SEALSQ Unveils VaultIC409 Secure Element for Post-Quantum Cryptography
The Quantum Insider · 12 oct. 2026