Abstract
LLM-agent simulations make natural-language social scenarios easy to instantiate, but their outputs can be overread as predictions and are often difficult to compare with explicit social dynamics. We present AgoraSim, a hybrid agent-based modeling framework for scenario-oriented social reaction analysis.
AgoraSim resolves textual or multimodal artifacts into editable ABM configurations, runs ratio-controlled populations that mix LLM, vision-language, custom-endpoint, random, and classical agents, and compares the same scenario against matched classical reference dynamics. All agents emit a shared structured decision object, enabling common action spaces, interaction protocols, metrics, and audit records.
AgoraSim helps users inspect scenario trajectories, compare modeling assumptions, and identify cases that warrant empirical validation through a local UI, Python SDK/CLI, and REST API.
Blogger's Review: The emergence of AgoraSim brings a new perspective to modeling social dynamics, especially with its hybrid approach combining LLM and classical agents. This flexibility not only enhances usability but also provides robust support for empirical research.