An Agentic Flow for Finite State Machine Extraction using Prompt Chaining
This work addresses the need for accurate FSM extraction in cybersecurity and reverse engineering, offering a novel method for protocol analysis, though it appears incremental as it builds on existing LLM techniques.
The paper tackled the problem of extracting Finite-State Machines (FSMs) from network protocol specifications, which is limited by scalability and ambiguity in existing methods, and proposed FlowFSM, an agentic framework using LLMs with prompt chaining, achieving high extraction precision and minimized hallucinated transitions in experiments on FTP and RTSP protocols.
Finite-State Machines (FSMs) are critical for modeling the operational logic of network protocols, enabling verification, analysis, and vulnerability discovery. However, existing FSM extraction techniques face limitations such as scalability, incomplete coverage, and ambiguity in natural language specifications. In this paper, we propose FlowFSM, a novel agentic framework that leverages Large Language Models (LLMs) combined with prompt chaining and chain-of-thought reasoning to extract accurate FSMs from raw RFC documents. FlowFSM systematically processes protocol specifications, identifies state transitions, and constructs structured rule-books by chaining agent outputs. Experimental evaluation across FTP and RTSP protocols demonstrates that FlowFSM achieves high extraction precision while minimizing hallucinated transitions, showing promising results. Our findings highlight the potential of agent-based LLM systems in the advancement of protocol analysis and FSM inference for cybersecurity and reverse engineering applications.