{"ID":6023456,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-10T08:31:24.850006579Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05999","arxiv_id":"2607.05999","title":"AgoraSim: A Hybrid Agent-Based Modeling Framework","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. Exposed through a local UI, Python SDK/CLI, and REST API, AgoraSim helps users inspect scenario trajectories, compare modeling assumptions, and identify cases that warrant empirical validation.","short_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 resol...","url_abs":"https://arxiv.org/abs/2607.05999","url_pdf":"https://arxiv.org/pdf/2607.05999v1","authors":"[\"Chung-Chi Chen\"]","published":"2026-07-07T08:37:17Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}