AutoPLC
Research generator for vendor-specific Structured Text, evaluated on Siemens SCL and CODESYS with a compiler in the loop.
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:2412.02410. The authors report above 90% compilation success on a 914-task mix (OSCAT, LGF, and a competition set) for Siemens SCL and CODESYS ST, at about $0.13 per task, and a 78% formal-verification pass on the 23-task Agents4PLC set. Compilation is not plant success. PLCWorld later adapted AutoPLC and did not find a consistent closed-loop gain. The repo includes the benchmarks they used.
Protocols
Sources
This page: https://otaihub.com/tools/autoplc
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.
- LLM4PLCResearch pipeline that loops an LLM with grammar checks, a compiler, and an SMV verifier to produce Structured Text.