Programming Manufacturing Robots with Imperfect AI: LLMs as Tuning Experts for FDM Print Configuration Selection

TL;DR

This paper demonstrates how large language models can serve as tuning experts within a Bayesian optimization framework to improve 3D printing configurations, outperforming single-shot AI recommendations.

Contribution

It introduces a modular closed-loop system integrating LLMs with Bayesian optimization for manufacturing robot configuration tuning, showing significant performance improvements.

Findings

LLM-guided tuning achieves 78% success rate on print quality.

Single-shot AI recommendations have only 15% success and higher failure risk.

The approach outperforms traditional AI suggestions in iterative optimization.

Abstract

We use fused deposition modeling (FDM) 3D printing as a case study of how manufacturing robots can use imperfect AI to acquire process expertise. In FDM, print configuration strongly affects output quality. Yet, novice users typically rely on default configurations, trial-and-error, or recommendations from generic AI models (e.g., ChatGPT). These strategies can produce complete prints, but they do not reliably meet specific objectives. Experts iteratively tune print configurations using evidence from prior prints. We present a modular closed-loop approach that treats an LLM as a source of tuning expertise. We embed this source of expertise within a Bayesian optimization loop. An approximate evaluator scores each print configuration and returns structured diagnostics, which the LLM uses to propose natural-language adjustments that are compiled into machine-actionable guidance for optimization. On 100 Thingi10k parts, our LLM-guided loop achieves the best configuration on 78% objects with 0% likely-to-fail cases, while single-shot AI model recommendations are rarely best and exhibit 15% likely-to-fail cases. These results suggest that LLMs provide more value as constrained decision modules in evidence-driven optimization loops than as end-to-end oracles for print configuration selection. We expect this result to extend to broader LLM-based robot programming.