{"slug": "llm-driven-automl-for-cross-lingual-handwritten-ocr-closed-loop-neural-search-5", "title": "LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4", "summary": "A new closed-loop AutoML framework using GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture designers achieves mean test accuracies above 93% and a best accuracy of 98.1% for cross-lingual handwritten OCR across Arabic, Persian, and English datasets, with inference latency between 41 and 44 milliseconds. The framework, evaluated through 270 independent experiments, eliminates manual architecture design and hyperparameter tuning, demonstrating that large language models can serve as effective AutoML agents for neural architecture search.", "body_md": "arXiv:2607.15509v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/llm-driven-automl-for-cross-lingual-handwritten-ocr-closed-loop-neural-search-5", "canonical_source": "https://arxiv.org/abs/2607.15509", "published_at": "2026-07-20 04:00:00+00:00", "updated_at": "2026-07-20 13:56:29.464061+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "machine-learning", "computer-vision", "ai-agents"], "entities": ["GPT-5", "GPT-4o", "Claude Sonnet 4", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/llm-driven-automl-for-cross-lingual-handwritten-ocr-closed-loop-neural-search-5", "markdown": "https://wpnews.pro/news/llm-driven-automl-for-cross-lingual-handwritten-ocr-closed-loop-neural-search-5.md", "text": "https://wpnews.pro/news/llm-driven-automl-for-cross-lingual-handwritten-ocr-closed-loop-neural-search-5.txt", "jsonld": "https://wpnews.pro/news/llm-driven-automl-for-cross-lingual-handwritten-ocr-closed-loop-neural-search-5.jsonld"}}