# Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing

arXiv: https://arxiv.org/abs/2605.04003 · HTML: https://mlsanity.com/paper/2605.04003/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 8 of 8)

- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Large Language Models for Manufacturing](https://mlsanity.com/paper/2410.21418/) (2024)
- [Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?](https://mlsanity.com/paper/2501.15795/) (2025)
- [Large Language Model-Enabled Multi-Agent Manufacturing Systems](https://mlsanity.com/paper/2406.01893/) (2024)
- [Towards Foundational AI Models for Additive Manufacturing: Language Models for G-Code Debugging, Manipulation, and Comprehension](https://mlsanity.com/paper/2309.02465/) (2023)
- [GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback](https://mlsanity.com/paper/2501.17584/) (2025)
- [Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planning](https://mlsanity.com/paper/2506.13026/) (2025)
- [Evaluation of Large Language Model-Driven AutoML in Data and Model Management from Human-Centered Perspective](https://mlsanity.com/paper/2507.05962/) (2025)

## Abstract (arXiv)

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 ≥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 10-2in to approximately ± 10-3in over most of the blade within the simulation environment, providing a pre-deployment verification signal for risk-aware human decision-making.