MASim: Multilingual Agent-Based Simulation for Social Science

ACL ARR 2026 January Submission2236 Authors

Keywords: Agent-based Simulation, Multilingual LLMs, Social Science Discovery

Abstract: Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual and fail to model cross-lingual interaction, an essential property of real societies. We introduce MASim, the first multilingual agent-based simulation framework that supports multi-turn interaction among generative agents with diverse sociolinguistic profiles. MASim offers two key analyses: (i) global public opinion modeling, by simulating how attitudes toward open-domain hypotheses evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To instantiate simulations, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on calibration, sensitivity, consistency, and cultural case studies show that MASim reproduces sociocultural phenomena and highlights the importance of multilingual simulation for scalable, controlled computational social science.

Paper Type: Long

Research Area: Computational Social Science, Cultural Analytics, and NLP for Social Good

Research Area Keywords: NLP tools for social analysis, quantitative analyses of news and social media, multilingualism

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English, Japanese, Portuguese, Spanish, Korean, Dutch

Submission Number: 2236