Agents4PLC
Multi-agent research framework and a verifiable Structured Text benchmark with formal specs and reference code.
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:2410.14209. The authors report, on their benchmark, a best verifiable rate of 68% and pass rate of 50% on Easy with GPT-4o, and 42.3% verifiable / 28.6% pass on Medium with GPT-4o. The public repo includes the benchmark and an LLM4PLC baseline. The README says the full agent implementation is withheld because of industrial partners. Do not treat the GitHub tree as a drop-in copilot.
Protocols
Sources
- Release repohttps://github.com/Luoji-zju/Agents4PLC_release
- arXivhttps://arxiv.org/abs/2410.14209
This page: https://otaihub.com/tools/agents4plc
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.
- LLM4PLCResearch pipeline that loops an LLM with grammar checks, a compiler, and an SMV verifier to produce Structured Text.
- AutoPLCResearch generator for vendor-specific Structured Text, evaluated on Siemens SCL and CODESYS with a compiler in the loop.