Paolo Giorgini

Marco Robol, Paolo Giorgini

Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software agents, combining BDI reasoning with LLMs to enable autonomous evolution of goals, reasoning, and executable code. We propose a BDI-LLM architecture in which an automated evolution module operates alongside the agent's reasoning loop, eliciting new requirements from experience and synthesizing corresponding design and code updates. A prototype evaluated in a dynamic multi-agent environment shows that agents can autonomously discover new goals and generate executable behaviours from minimal prior knowledge. The results indicate both the feasibility and current limits of LLM-driven evolution, particularly in terms of behavioural inheritance and stability.

Mohamad Gharib, Paolo Giorgini, John Mylopoulos

Privacy has been frequently identified as a main concern for system developers while dealing with/managing personal information. Despite this, most existing work on privacy requirements deals with them as a special case of security requirements. Therefore, key aspects of privacy are, usually, overlooked. In this context, wrong design decisions might be made due to insufficient understanding of privacy concerns. In this paper, we address this problem with a systematic literature review whose main purpose is to identify the main concepts/relations for capturing privacy requirements. In addition, the identified concepts/relations are further analyzed to propose a novel privacy ontology to be used by software engineers when dealing with privacy requirements.

Chi Mai Nguyen, Roberto Sebastiani, Paolo Giorgini et al.

We are interested in supporting software evolution caused by changing requirements and/or environmental settings. For example, users of a system may require new functionality (changing requirements), or performance enhancements to cope with growing user population. Specifically, we propose to use goal models to capture such changes, and exploit reasoning techniques that derive optimal new specifications for a system whose requirements and/or environment have changed. Moreover, we are interested in discovering new classes of evolution requirements, for example, that give preference to evolutions that minimize implementation effort for the implementation of the evolution. To address both of these problems, we exploit Constraint Goal Models (CGMs) an expressive language for modelling goals that comes with scalable solvers that can solve hybrid constraint and optimization problems using a combination of Satisfiability Modulo Theories (SMT) and Optimization Modulo Theories (OMT) solvers. We evaluate our proposal by modeling and reasoning with a goal model for meeting scheduling.

Chi Mai Nguyen, Roberto Sebastiani, Paolo Giorgini et al.

Goal models have been widely used in Computer Science to represent software requirements, business objectives, and design qualities. Existing goal modelling techniques, however, have shown limitations of expressiveness and/or tractability in coping with complex real-world problems. In this work, we exploit advances in automated reasoning technologies, notably Satisfiability and Optimization Modulo Theories (SMT/OMT), and we propose and formalize: (i) an extended modelling language for goals, namely the Constrained Goal Model (CGM), which makes explicit the notion of goal refinement and of domain assumption, allows for expressing preferences between goals and refinements, and allows for associating numerical attributes to goals and refinements for defining constraints and optimization goals over multiple objective functions, refinements and their numerical attributes; (ii) a novel set of automated reasoning functionalities over CGMs, allowing for automatically generating suitable refinements of input CGMs, under user-specified assumptions and constraints, that also maximize preferences and optimize given objective functions. We have implemented these modelling and reasoning functionalities in a tool, named CGM-Tool, using the OMT solver OptiMathSAT as automated reasoning backend. Moreover, we have conducted an experimental evaluation on large CGMs to support the claim that our proposal scales well for goal models with thousands of elements.