Physics-grounded multi-agent architecture for traceable, risk-aware human–AI decision support in manufacturing

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 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, and a residual systematic compliance term. In a three-level tool-orchestration benchmark spanning single-step to three-or-more-step stateful sequences, MAKA increased the pass rate for correct tool selection, argument assignment, and dependency-consistent execution by a mean, median, and maximum of 22.9, 8.0, and 64.0 percentage points, respectively, across 15 model-level comparisons over the stronger of the ReAct-style and structured function-calling baselines with identical model and tool access. Digital twin what-if studies show MAKA can coordinate traceable compensation candidates that reduce predicted surface deviation from order 1 0 − 2 in to approximately ± 1 0 − 3 in over most of the blade within the simulation environment, providing a pre-deployment verification signal for risk-aware human decision-making.