paper-with-me

Papers

LLM4SFC: Sequential Function Chart Generation via Large Language Models

2025-12-07 · Ofek Glick, Vladimir Tchuiev, Marah Ghoummaid, Michal Moshkovitz, Dotan Di-Castro arxiv

While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain underexplored. Generating SFCs is challenging due to graphical nature and ST actions embedded within, which are not directly compatible with standard generation techniques, often leading to non-executable code that is incompatible with industrial tool-chains In this work, we introduce LLM4SFC, the first framework to receive natural-language descriptions of industrial workflows and provide executable SFCs. LLM4SFC is based on three components: (i) A reduced structured representation that captures essential topology and in-line ST and reduced textual verbosity; (ii) Fine-tuning and few-shot retrieval-augmented generation (RAG) for alignment with SFC programming conventions; and (iii) A structured generation approach that prunes illegal tokens in real-time to ensure compliance with the textual format of SFCs. We evaluate LLM4SFC on a dataset of real-world SFCs from automated manufacturing projects, using both open-source and proprietary LLMs. The results show that LLM4SFC reliably generates syntactically valid SFC programs effectively bridging graphical and textual PLC languages, achieving a generation generation success of 75% - 94%, paving the way for automated industrial programming.

📄 PDF Abstract BibTeX arXiv:2512.06787

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data

2025-03-20 · Zijian Li, Jingjing Fu, Lei Song, Jiang Bian 외

Visual reasoning is crucial for multimodal large language models (MLLMs) to address complex chart queries, yet high-quality rationale data remains scarce. Existing methods leveraged (M)LLMs for data generation, but direc…

DiversityVisual Reasoning

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

2025-01-11 · Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen 외

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in chart understanding tasks. However, interpreting charts with textual descriptions often leads to information loss, as it fails to full…

Chart UnderstandingCode GenerationLanguage ModelingLanguage Modelling+2

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability

2025-06-02 · Mengliang He, Jiayi Zeng, Yankai Jiang, Wei zhang 외

While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow…

Code Generation

Enhancing Chart-to-Code Generation in Multimodal Large Language Models via Iterative Dual Preference Learning

2025-04-03 · Zhihan Zhang, Yixin Cao, Lizi Liao

Chart-to-code generation, the process of converting chart images into executable plotting scripts, provides a lossless representation of chart information, requiring models to accurately capture and summarize all visual …

Code Generation

Effective Training Data Synthesis for Improving MLLM Chart Understanding

2025-08-08 · Yuwei Yang, Zeyu Zhang, Yunzhong Hou, Zhuowan Li 외 arxiv

Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source …