LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4

2026-07-16

AI Summary

This work addresses the reliance on manually designed network architectures, preprocessing pipelines, and hyperparameter tuning in cross-lingual handwritten OCR by introducing the first large language model–based closed-loop AutoML framework. The proposed approach innovatively employs GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous agents to perform end-to-end neural architecture search, training, evaluation, and iterative optimization without human intervention. Evaluated on handwritten datasets in Arabic, Persian, and English, the framework achieves an average accuracy exceeding 93%, with a peak performance of 98.1%, while maintaining low inference latency of 41–44 milliseconds. These results demonstrate a significant advancement in both automation and performance for cross-lingual handwritten text recognition.

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.

Problem

• Cross-Lingual OCR
• Handwritten Character Recognition
• Neural Architecture Search
• AutoML
• Multilingual Handwriting

Innovation

• LLM-driven AutoML
• closed-loop neural architecture search
• cross-lingual handwritten OCR
• autonomous architecture design
• script-adaptive recognition