Large language model (LLM) agents increasingly operate in groups, each pursuing an individual objective while jointly determining system performance. If an operator controls which agent observes which other agent, but not their payoffs or messages, how should observations be structured to raise collective welfare? We m...
Dashboards, feeds, and leaderboards determine whom agents believe they are playing against. We study how such information architectures shape strategic behavior, and how a designer who controls them can use visibility as a lever. We propose a behavioral model in which a transparency parameter governs how selectively ag...
Raman Ebrahimi, S. Ilami, Babak Heydari et al.· 0 citations
Large language models are increasingly deployed as interacting agents, making the persistence of their action policies across repeated interaction critical for reliable multi-agent operation. We investigate whether and how agent-generated, non-binding pre-play communication ("cheap talk") increases such persistence in...
Human-AI interaction can improve current performance while changing the capabilities and relationships on which future performance depends. We develop adaptive complementarity, a framework for choosing interaction architecture with these state consequences in view. Access, information exposure, task allocation, timing,...
Babak Heydari· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.