Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties
Preprint
Abstract
Can large language model (LLM) agents reproduce the complex social dynamics that characterize human online behavior -- shaped by homophily, reciprocity, and social validation -- and what memory and learning mechanisms enable such dynamics to emerge? We present a multi-agent LLM simulation framework in which agents repeatedly interact, evaluate one another, and adapt their behavior through in-context learning accelerated by a coaching signal. To model human social behavior, we design behavioral reward functions that capture core drivers of online engagement, including social interaction, information seeking, self-presentation, coordination, and emotional support. These rewards align agent objectives with empirically observed user motivations, enabling the study of how network structures and group formations emerge from individual decision-making. Our experiments show that coached LLM agents develop stable interaction patterns and form emergent social ties, yielding network structures that mirror properties of real online communities. By combining behavioral rewards with in-context adaptation, our framework establishes a principled testbed for investigating collective dynamics in LLM populations and reveals how artificial agents may approximate or diverge from human-like social behavior.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- On the conversational persuasiveness of GPT-4Nature Human Behaviour, 2025
- Large language models empowered agent-based modeling and simulation: a survey and perspectivesHumanities and Social Sciences Communications, 2024
- Out of One, Many: Using Language Models to Simulate Human SamplesPolitical Analysis, 2023
- Community detection in graphsPhysics Reports, 2010
- Introduction to stochastic actor-based models for network dynamicsSocial Networks, 2010
- Structure and tie strengths in mobile communication networksProceedings of the National Academy of Sciences, 2007
- The Mini-IPIP Scales: Tiny-yet-effective measures of the Big Five Factors of Personality.Psychological Assessment, 2006
- Evolution of indirect reciprocityNature, 2005
- Personality trait structure as a human universal.American Psychologist, 1997
- The development of markers for the Big-Five factor structure.Psychological Assessment, 1992