Version note. This entry corresponds to the revised camera-ready manuscript accepted at FAIEMA 2026. It is distinct from the earlier arXiv preprint, “Evaluating Cooperative …
In this talk, I presented our pilot study comparing cooperative resilience in human groups and LLM-based multi-agent systems under disruptions.
Abstract. Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems …
A selection of foundational and recent papers that have shaped how I think about cooperation, mixed-motive environments, reward learning, LLM-based agents, and resilience in …