← 피드로
[Submitted on 16 Jul 2026 (v1), last revised 18 Aug 2026 (this version, v3)]
Abstract:We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers for cross-lingual handwritten optical character recognition. Each large language model independently generates, trains, evaluates, and iteratively refines neural network architectures using performance feedback from previous trials. The framework is evaluated on Arabic, Persian, and English handwriting datasets through 270 independent experiments. It consistently discovers accurate and computationally efficient models without manual architecture design, domain-specific preprocessing, or hyperparameter tuning. The generated models achieve mean test accuracies above 93 percent, a best accuracy of 98.1 percent, and inference latency between 41 and 44 milliseconds. The results demonstrate that large language models can function as effective AutoML agents for neural architecture search, enabling scalable, script-adaptive, and reproducible handwriting recognition across languages.
Submission history
From: Mobina Kashaniyan [view email]
[v1]
Thu, 16 Jul 2026 23:43:23 UTC (1,755 KB)
[v2]
Mon, 10 Aug 2026 03:39:39 UTC (1,755 KB)
[v3]
Tue, 18 Aug 2026 21:13:45 UTC (1,756 KB)
추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2607.15509