LLM4PLC
Research pipeline that loops an LLM with grammar checks, a compiler, and an SMV verifier to produce Structured Text.
Who it's for
People comparing published PLC-code or controller-agent results. The number on this page is only as good as the paper or site it cites.
Caveat / limitations
Paper: arXiv:2401.05443, Fakih et al. On their Fischertechnik manufacturing testbed they report generation success moving from 47% to 72% with the pipeline, and an expert quality score from 2.25/10 to 7.75/10. Those numbers are that study, not AutoFactory-Bench or PLCWorld. Later papers use LLM4PLC as a baseline with different scaffolding. The code repo is public.
Protocols
Sources
This page: https://otaihub.com/tools/llm4plc
Same category
- AutoFactory-BenchClosed-loop benchmark: agents write one Structured Text file for 100 factory tasks and a simulator grades success and safety.
- PLCWorldResearch benchmark of 100 Structured Text tasks graded in closed loop, with task success and safety reported separately.
- Agents4PLCMulti-agent research framework and a verifiable Structured Text benchmark with formal specs and reference code.
- AutoPLCResearch generator for vendor-specific Structured Text, evaluated on Siemens SCL and CODESYS with a compiler in the loop.