Adaptive Social Learning using Theory of Mind

2025-07-12

AI Summary

This study investigates how humans adaptively balance social learning and individual exploration to optimize goal achievement. We propose the first rational theory-of-mind (ToM)-based social learning model that dynamically estimates the expected utility of social learning by inferring others’ goals and the informational value of their actions. Crucially, our model introduces explicit mental-state inference into social learning decisions—marking the first formal integration of ToM into quantitative models of human social learning. We combine utility estimation with multi-agent cooperative game theory and validate the model in a multi-player treasure-hunt task. Results demonstrate that the model not only quantitatively reproduces key human behavioral patterns—including information-sampling preferences and dynamic trust updating—but also enables artificial agents to autonomously integrate social and individual learning strategies. This leads to significant improvements in task efficiency and generalization across novel environments.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Social networks and social learning
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

Social learning is a powerful mechanism through which agents learn about the world from others. However, humans don't always choose to observe others, since social learning can carry time and cognitive resource costs. How do people balance social and non-social learning? In this paper, we propose a rational mentalizing model of the decision to engage in social learning. This model estimates the utility of social learning by reasoning about the other agent's goal and the informativity of their future actions. It then weighs the utility of social learning against the utility of self-exploration (non-social learning). Using a multi-player treasure hunt game, we show that our model can quantitatively capture human trade-offs between social and non-social learning. Furthermore, our results indicate that these two components allow agents to flexibly apply social learning to achieve their goals more efficiently.

Problem

• Balancing social and non-social learning costs
• Modeling utility of social learning decisions
• Quantifying human trade-offs in learning strategies

Innovation

• Rational mentalizing model for social learning
• Balances social and non-social learning utilities
• Multi-player game validates human-like trade-offs