Tag
This paper shows that adding preceding gameplay dialogue context significantly improves LLM-based detection of deceptive statements in the hidden role game Avalon, with accuracy gains of up to 31% over message-only approaches.
This paper introduces Differentiable Belief-based Opponent Shaping (D-BOS), a first-order method that treats observer beliefs as the shaped state and differentiates through belief update dynamics, allowing optimal strategies to emerge naturally from the environment's reward structure in hidden-role multi-agent settings.