{"slug": "machine-readable-operator-manuals-over-the-iso-11783-network-for-offline-llm", "title": "Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance", "summary": "A proof-of-concept study (arXiv:2610.31863v1) transferred a complete agricultural implement operator manual over a physical ISO 11783 CAN bus in 31 to 89 seconds, depending on format and transport settings, a delay comparable to the object pool upload operators already wait for when first coupling an implement. Benchmarking Markdown, JSON and XML, the researchers found Markdown produced the smallest files while question-answering performance was comparable across formats for most models; with retrieval-augmented generation, locally run open-weight LLMs answered most questions on the English manual correctly with no advantage for the largest model over 7B and 8B models, but performed worse on the five other language editions, and keyword retrieval failed across languages where semantic retrieval succeeded. The exchange needs only a new parameter group using ISO 11783's existing request and transport mechanisms, making it a candidate for standardization, though inference ran on PC-grade hardware and deployment on embedded agricultural hardware remains future work.", "body_md": "arXiv:2610.31863v1 Announce Type: new \nAbstract: If agricultural machinery is to support intelligent, offline assistance, then the system must access technical documentation dynamically. In this paper, the Semantic Synchronization of operator manuals over ISO 11783-based CAN buses is analyzed, defined as the process that brings the local knowledge base of a tractor-side assistant into agreement with the operator manual of the connected implement. Data transfer performance was benchmarked using Markdown, JSON, and XML; various open-weight Large Language Models (LLMs) were also evaluated in cross-lingual query tasks. The automatic evaluation of the answers was validated against four human raters. A complete manual was transferred over a physical ISO 11783 network in 31 to 89 s, depending on format and transport settings, which is comparable to the object pool upload that operators already wait for at the first coupling of an implement. Markdown produced the smallest files, while the question-answering performance was comparable across the three formats for most models. With retrieval-augmented generation, locally run models answered most questions on the English manual correctly, with no advantage of the largest model over 7B and 8B models, but performed worse on the five other language editions. Keyword retrieval failed across languages, whereas semantic retrieval provided the cross-lingual capability. The exchange requires only a new parameter group that uses the existing request and transport mechanisms of ISO 11783, which makes it a candidate for standardization. The study is a proof of concept with inference on PC-grade hardware; deployment on embedded agricultural hardware remains future work.", "url": "https://wpnews.pro/news/machine-readable-operator-manuals-over-the-iso-11783-network-for-offline-llm", "canonical_source": "https://arxiv.org/abs/2610.31863", "published_at": "2026-10-26 04:00:00+00:00", "updated_at": "2026-10-26 04:13:22.946080+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "natural-language-processing", "ai-agents"], "entities": ["ISO 11783", "arXiv", "Markdown", "JSON", "XML"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/machine-readable-operator-manuals-over-the-iso-11783-network-for-offline-llm", "markdown": "https://wpnews.pro/news/machine-readable-operator-manuals-over-the-iso-11783-network-for-offline-llm.md", "text": "https://wpnews.pro/news/machine-readable-operator-manuals-over-the-iso-11783-network-for-offline-llm.txt", "jsonld": "https://wpnews.pro/news/machine-readable-operator-manuals-over-the-iso-11783-network-for-offline-llm.jsonld"}}