Towards LLM-Assisted Architecture Recovery for Real-World ROS~2 Systems: An Agent-Based Multi-Level Approach to Hierarchical Structural Architecture Reconstruction
For developers of ROS~2-based robotic systems, this work incrementally improves automated hierarchical architecture recovery from distributed artifacts, addressing a known bottleneck in recovering structural decomposition across abstraction levels.
The paper enhances an LLM-assisted architecture recovery pipeline for ROS~2 systems by refining prompts and introducing a staged recovery strategy with multi-level intermediate representations. Evaluated on a complex real-world robotic disassembly system, the approach shows improved structural consistency, scalability, and robustness.
Explicit software architecture models are essential artifacts for communicating, analyzing, and evolving complex software-intensive systems. In ROS~2-based robotic systems, however, structural (de-)composition and integration semantics are often only implicitly encoded across distributed artifacts such as source code and launch files, making recovery of hierarchical architecture particularly difficult. Existing approaches mainly focus on node-level entities and communication wiring, while providing limited support for recovering hierarchical structural (de-)composition across multiple abstraction levels. In this paper, we extend our previously proposed blueprint-guided LLM-assisted architecture recovery pipeline for ROS~2 systems through two major enhancements: (1) refined prompting to improve the consistency and controllability of architecture synthesis, and (2) a staged recovery strategy based on multi-level intermediate architectural representations that incorporate the atomic ROS node list and launch file dependencies, thereby enabling structurally constrained reconstruction across multiple abstraction levels. The approach is evaluated on a real-world automated product disassembly system based on cooperative robotic arms and heterogeneous ROS~2 artifacts. Compared to our previous work, the considered case study exhibits substantially higher integration complexity and richer functionality. The results demonstrate improved structural consistency, scalability, and robustness of architecture recovery, while also revealing remaining challenges related to dynamic integration semantics in large-scale ROS~2 systems.