11 papers
Bathtubs, Boundaries, and Sandboxes: AI Regulatory Learning under Legal Uncertainty
Tom Deckenbrunnen, Alessio Buscemi, Marco Almada +2
Effective regulation of AI is a defining policy challenge, driven by their integration into all aspects of society. To remain responsive to their rapid development and emergent pro…
Payoff scaling shapes cooperation in LLM agents across languages
Trung-Kiet Huynh, Dao-Sy Duy-Minh, Thanh-Bang Cao +13
Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they cooperate in such settings is no lo…
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…
Assessing High-Risk AI Systems under the EU AI Act: From Legal Requirements to Technical Verification
Alessio Buscemi, Tom Deckenbrunnen, Fahria Kabir +2
The implementation of the AI Act requires practical mechanisms to verify compliance with legal obligations, yet concrete and operational mappings from high-level requirements to ve…
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…
Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics
Trung-Kiet Huynh, Duy-Minh Dao-Sy, Thanh-Bang Cao +13
As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behavio…