Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing
On the map: LLM agents and tool use → Multimodal and embodied agents
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.
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.
Builds on
8 of 42 references.
References · 8
- 2024Tool Learning with Large Language Models: A Surveycited by 223
- 2024Large Language Models for Manufacturingcited by 24
- 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?cited by 17
- 2024Large Language Model-Enabled Multi-Agent Manufacturing Systemscited by 14
- 2023Towards Foundational AI Models for Additive Manufacturing: Language Models for G-Code Debugging, Manipulation, and Comprehensioncited by 9
- 2025GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedbackcited by 3
- 2025Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planningcited by 3
- 2025Evaluation of Large Language Model-Driven AutoML in Data and Model Management from Human-Centered Perspectivecited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution
- 2025Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Framework
- 2025A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models
- 2026Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
- 2026From Perception to Autonomous Computational Modeling: A Multi-Agent Approach
- 2025Intelligent Human-Machine Partnership for Manufacturing: Enhancing Warehouse Planning through Simulation-Driven Knowledge Graphs and LLM Collaboration
- 2026Constrained Process Maps for Multi-Agent Generative AI Workflows
- 2025MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning