Michele Albano

Davide Taibi, Henry Muccini, Karthik Vaidhyanathan et al.

The rise of agentic AI is reshaping software engineering in two intertwined directions: agents are increasingly applied to support software engineering tasks, and Agentic AI systems themselves are complex systems that require re-thinking currently established software engineering practices. To chart a coherent research agenda covering the two directions, we organized the A2SE seminar in Rio de Janeiro, bringing together 18 experts from academia and industry. Through structured presentations, collaborative topic clustering, and focused group discussions, participants identified six thematic areas: Governance, Software Engineering for Agents, Agents for Software Architecture, Quality and Evaluation, Sustainability, and Code, and they prioritized short-term and long-term research directions for each. This paper presents the resulting community-driven, opinionated research agenda, offering the SE community a structured foundation for coordinating efforts at this critical juncture.

Antheas Kapenekakis, Bent Thomsen, Katja Hose et al.

To generate synthetic datasets, e.g., in domains such as healthcare, the literature proposes approaches of two main types: Probabilistic Graphical Models (PGMs) and Deep Learning models, such as LLMs. While PGMs produce synthetic data that can be used for advanced analytics, they do not support complex schemas and datasets. LLMs on the other hand, support complex schemas but produce skewed dataset distributions, which are less useful for advanced analytics. In this paper, we therefore present Amalgam, a hybrid LLM-PGM data synthesis algorithm supporting both advanced analytics, realism, and tangible privacy properties. We show that Amalgam synthesizes data with an average 91 % $χ^2 P$ value and scores 3.8/5 for realism using our proposed metric, where state-of-the-art is 3.3 and real data is 4.7.

Anders Aaen Springborg, Martin Kaldahl Andersen, Kaare Holland Hattel et al.

Given the success of IoT platforms, more developers and companies want to include the technology in their portfolio. However, in the case of single board microcontrollers, the support for networking operations is not ideal, and different IoT platforms allow access to the networking submodule via different libraries and system calls, leading to a steeper learning curve. Code generators for API clients can enhance productivity, but they tend to generate universal purpose code, and on the other hand the networking primitives of IoT devices are platform specific, especially when security mechanisms such as Transport Layer Security are part of the picture. This paper presents \texttt{cpp-tiny-client}, an API client generator developed as a plugin for the OpenAPI Generator project, which can tailor the generated code based on the IoT platform specified by the user. Our work allows to generate correct code for API clients for IoT devices, and thus can empower a developer with more productivity and a faster time-to-market for its own applications. By combining together mainstream technologies only, \texttt{cpp-tiny-client} offers a gentle learning curve. Moreover, experiments show that the generated code has a reasonable footprint, at least with respect to the IoT devices that were used in the validation of the work. The code related to this work is available through the OpenAPI Generator project~\cite{OpenAPIGenerator}. This technical report is an extension of~\cite{acmsac22}, and it integrates the information presented at the ACM SAC 2022 conference.