Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing
Danny Hoang, Ryan Matthiessen, Christopher Miller, Nasir Mannan, Ruby ElKharboutly, David Gorsich, Matthew P. Castanier, Farhad Imani
Why It Matters
What makes this one worth your time
This work is relevant for AI researchers and engineers focused on manufacturing, as it proposes a structured approach to integrate AI with human decision-making, potentially improving precision and safety in high-stakes environments.
MAKA enhances decision support in CNC machining by integrating multi-agent systems for improved traceability and risk awareness.
Summary
The paper presents a multi-agent architecture called MAKA for decision support in CNC machining, integrating inspection, simulation, and process knowledge to improve tool execution and traceability in manufacturing processes.
Key contributions
- Introduction of the MAKA architecture for human-AI decision support.
- Demonstration of improved tool execution in CNC machining through a structured multi-agent approach.
- Integration of virtual-machining path-tracking and simulation data for enhanced decision-making.
Notable insights
- The use of a critic-based verification system to enforce physical plausibility and safety bounds before human approval.
- Decomposition of deviation into multiple components for better traceability and risk assessment.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2605.04003v1 Announce Type: cross Abstract: High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledge. Off-the-shelf large language model (LLM) assistants can generate text, but they do not reliably execute risk-constrained multi-step numerical workflows or provide auditable provenance for high-stakes decisions. We present multi-agent knowledge analysis (MAKA), a human-in-the-loop decision-support architecture that separates intent routing, tools-only quantitative analysis, knowledge graph retrieval, and critic-based verification that enforces physical plausibility, safety bounds, and provenance completeness before recommendations are surfaced for human approval. MAKA is instantiated on a Ti-6Al-4V rotor blade machining testbed by fusing virtual-machining path-tracking error fields, cutting-force and deflection simulations, and scan-based 3D inspection deviation maps from 16 blades. The analysis decomposes deviation into an evidence-linked pathing component, a drift-based wear proxy capturing systematic evolution across parts, a residual systematic compliance term, and a variability proxy for instability-aware escalation. In a three-level tool-orchestration benchmark (single-step through $\geq$3-step stateful sequences), MAKA improves successful tool execution by up to 87.5 percentage points relative to an unstructured single-model interaction pattern with identical tool access. Digital twin what-if studies show MAKA can coordinate traceable compensation candidates that reduce predicted surface deviation from order $10^{-2}$in to approximately $\pm 10^{-3}$in over most of the blade within the simulation environment, providing a pre-deployment verification signal for risk-aware human decision-making.