P SM B ENCH : A Benchmark and Dataset for Evaluating LLMs Extraction of Protocol State Machines from RFC Specifications

R FC 2P SM is introduced, the first large-scale dataset that pairs 1,580 pages of cleaned RFC text with 108 manually validated states and 297 transitions covering 14 widely deployed protocols spanning the data-link, transport, session, and application layers, and a benchmark that feeds chunked RFC to an LLM, prompts the model to emit a machine-readable PSM, and scores the output with structure-aware, semantic fuzzy-matching metrics that reward partially correct graphs.