Theory of Mind (ToM) is the ability to understand and reflect on the mental states of others. Although this capability is crucial for human interaction, testing on Large Language Models (LLMs) reveals that they possess only a rudimentary understanding of it. Although the most capable closed-source LLMs have come close to human performance on some ToM tasks, they still perform poorly on complex variations of the task that involve more structured reasoning. In this work, we utilize the concept of “pretend-play”, or “Simulation Theory” from cognitive psychology to propose “Decompose-ToM”: an LLM-based inference algorithm that improves model performance on complex ToM tasks. We recursively simulate user perspectives and decompose the ToM task into a simpler set of tasks: subject identification, question-reframing, world model updation, and knowledge availability. We test the algorithm on higher-order ToM tasks and a task testing for ToM capabilities in a conversational setting, demonstrating that our approach shows significant improvement across models compared to baseline methods while requiring minimal prompt tuning across tasks and no additional model training. Our code is publicly available.

The online information ecosystem enables influence campaigns of unprecedented scale and impact. We urgently need empirically grounded approaches to counter the growing threat of malicious campaigns, now amplified by generative AI. But, developing defenses in real-world settings is impractical. Social system simulations with agents modelled using Large Language Models (LLMs) are a promising alternative approach and a growing area of research. However, existing simulators lack features needed to capture the complex information-sharing dynamics of platform-based social networks. To bridge this gap, we present SandboxSocial, a new simulator that includes several key innovations, mainly: (1) a virtual social media platform (modelled as Mastodon and mirrored in an actual Mastodon server) that enables a realistic setting in which agents interact; (2) an adapter that uses real-world user data to create more grounded agents and social media content; and (3) multi-modal capabilities that enable our agents to interact using both text and images---just as humans do on social media. We make the simulator more useful to researchers by providing measurement and analysis tools that track simulation dynamics and compute evaluation metrics to compare experimental results.

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.