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 what extent, different types of messages affect the outcomes of strategic games. By investigating AI agents based on four popular LLMs, playing...
Alessio Buscemi, Daniele Proverbio, A. Di Stefano et al.· 0 citations
This work model peer-to-peer (P2P) interactions on a lattice network structure under the assumption of bounded rationality and forms a comprehensive payoff matrix incorporating training costs, communication overhead, and cooperative rewards, while tailoring a strategy update rule that captures spatial propagation dynam...
Phuc Hoang Truong Huynh, Dung Tran Vinh, Khoa Duc Anh Lam et al.· 0 citations
Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful. This is prominent in debates about artificial intelligence (AI), where competitive pressure is often argued to incentivise riskier, less safety-conscious development. W...
Elias Fernández Domingos, T. Han· arXiv.org· 0 citations
The results show why multi-agent AI-race simulations need validity checks and trajectory-level analysis before their outputs are described as strategic, human-like, or safety-aware.
P. Pham, Duy Minh Dao Sy, Trung-Kiet Huynh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
