Newest papers

From Code Generator to Engineering Companion: A Plant-Aware Agent for PLC Programming

Joschka Kersting, Gesa A. Benndorf · 2026 · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)

DOI: 10.1109/etfa68377.2026.11725227 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

يظل تشغيل PLC (Programmable Logic Controller) عملًا عمليًا، يرتكز على IDE، ويتطلب تغييرًا مستمرًا بين الوثائق والملفات المشفرة والمعدات. وقد أظهرت العملات الأخيرة أن نموذج اللغة الكبيرة المتطورة التي تزيد من التخزين يمكن أن تنتج ملفات متنوعة متطورة متوافقة مع الموردين مع معدل التكوين العالي، ولكن هذه الأنظمة تتعامل مع إنتاج الكود كوسيلة واحدة: يقوم المهندس بإرسال استفسار ويحصل على الكود، دون معرفة مستمرة من المصنع المحدد. نحن نقدم نموذجًا متكاملًا يتعلم المصنع الذي يطمح إلى توسيع هذا النموذج في ثلاث طرق: استهلاك الوثائق المحددة

Machine translation (Meta M2M100); the English original follows.

Abstract

Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and code editors. Recent work has demonstrated that retrieval-augmented large language models can generate vendor-compliant Structured Text at high compilation rates \cite{pred}, yet these systems treat code generation as a one-shot pipeline: the engineer submits a query and receives code, with no persistent knowledge of the specific plant. We present a plant-aware conversational copilot that extends this paradigm in three directions: plant-specific context ingestion, a chat-first interaction model for explanation and debugging, and a graduated tool-access ladder from chat to deployment. The system is designed for real plant infrastructure and keeps the engineer in control of each step that produces real-world effects.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Code (set theory), Programmable logic controller, Generator (circuit theory), Code generation, Programming language

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28160, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange