Our paper “Modeling and Recovering Hierarchical Structural Architectures of ROS 2 Systems from Code and Launch Configurations using LLM-based Agents” has been accepted at ICSA 2026

The paper “Modeling and Recovering Hierarchical Structural Architectures of ROS 2 Systems from Code and Launch Configurations using LLM-based Agents” by Mohamed Benchat, Dominique Briechle, Raj Chanchad, Mitbhai Chauhan, Meet Chavda, Ruidi He, Dhruv Jajadiya, Dhruv Kapadiya, Nidhiben Kaswala, Daniel Osterholz, Andreas Rausch and Meng Zhang has been accepted at ICSA 2026, the 23^rd IEEE International Conference on Software Architecture. 

The International Conference on Software Architecture (ICSA) is the premier venue for practitioners and researchers interested in software architecture, in component-based software engineering and in quality aspects of software and how these relate to the design of software architectures.

ICSA has a strong tradition as a working conference (previously named Working International Conference on Software Architecture, WICSA), where researchers meet practitioners and software architects can explain the problems they face in their day-to-day work and try to influence the future of the field.

ICSA 2026 is scheduled to be held at the Vrije Universiteit Amsterdam, Netherlands, between the 22nd and the 26th of June 2026. Check out more about the history and past series of ICSA at https://icsa-conferences.org/series/history

Model-Driven Engineering (MDE) relies on explicit architecture models to document and evolve systems across abstraction levels. For ROS~2, subsystem structure is often encoded implicitly in distributed configuration artifacts -- most notably launch files -- making hierarchical structural decomposition hard to capture and maintain. Existing ROS~2 modeling approaches cover node-level entities and wiring, but do not make hierarchical structural (de-)composition a first-class architectural view independent of launch artifacts. 
We contribute (1) a UML-based modeling concept for hierarchical structural architectures of ROS~2 systems and (2) a blueprint-guided automated recovery pipeline that reconstructs such models from code and configuration artifacts by combining deterministic extraction with LLM-based agents. The ROS~2 architectural blueprint (nodes, topics, interfaces, launch-induced wiring) is encoded as structural contracts to constrain synthesis and enable deterministic validation, improving reliability. 
We evaluate the approach on three ROS~2 repositories, including an industrial-scale code subset. Results show high precision across abstraction levels, while subsystem-level recall drops with repository complexity due to implicit launch semantics, making high-level recovery the remaining challenge.

The full paper can be read at https://arxiv.org/abs/2602.18644