12 citations · 19 across the 8 of their papers we have counts for
9 papers
When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano +3
Large language model (LLM)-based agents increasingly operate in multi-agent systems (MAS) characterised by strategic interaction. However, little is known about whether, and to wha…
When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano +3
LLMs-based agents increasingly operate in multi-agent environments where strategic interaction and coordination are required. While existing work has largely focused on individual…
Can LLMs effectively provide game-theoretic-based scenarios for cybersecurity?
Daniele Proverbio, Alessio Buscemi, Alessandro Di Stefano +3
Game theory has long served as a foundational tool in cybersecurity to test, predict, and design strategic interactions between attackers and defenders. The recent advent of Large…
Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano +3
Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strateg…
FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano +3
Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustw…
Impact of the Covid 19 outbreaks on the italian twitter vaccination debat: a network based analysis
Veronica Lachi, Giovanna Maria Dimitri, Alessandro Di Stefano +3
Vaccine hesitancy, or the reluctance to be vaccinated, is a phenomenon that has recently become particularly significant, in conjunction with the vaccination campaign against COVID…
RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow
Samuel Glass, Simeon Spasov, Pietro Liò
A novel method to identify salient computational paths within randomly wired neural networks before training is proposed. The computational graph is pruned based on a node mass pro…
GRADE: Graph Dynamic Embedding
Simeon Spasov, Alessandro Di Stefano, Pietro Lio +1
Representation learning of static and more recently dynamically evolving graphs has gained noticeable attention. Existing approaches for modelling graph dynamics focus extensively…
A Novel Methodology for designing Policies in Mobile Crowdsensing Systems
Alessandro Di Stefano, Marialisa Scatà, Barbara Attanasio +3
Mobile crowdsensing is a people-centric sensing system based on users' contributions and incentive mechanisms aim at stimulating them. In our work, we have rethought the design of…