MSc in Computer Science and Engineering, University of Bologna.
I work on LLM-based agents and how to evaluate them -- cognitive architectures for language agents, the bridge between symbolic (BDI) and generative approaches, and agent robustness in dynamic environments.
- coag-framework -- Cognitive AutoGen: extends AutoGen with a CoALA-inspired cognitive layer, plus the adversarial testbed used to evaluate it against a purely generative baseline
- genai-agents -- experiments from my MSc thesis: generative, cognitive and symbolic agents compared in a stochastic environment
- DCCV -- distributed computer vision framework on the actor model (Scala/Akka), with DDD, Docker Swarm and CI/CD
LLM agents · cognitive architectures (CoALA) · agent-oriented programming · agent evaluation and benchmarking · multi-agent systems · distributed systems