用混合智能体模拟社会反应，让大模型推理更可比、可审计。
AgoraSim: A Hybrid Agent-Based Modeling Framework
- 融合大模型、视觉语言等多类智能体，统一决策输出格式。
- 支持比率控制的混合种群实验，可对比经典模型与新方法。
- 提供本地界面和接口，便于分析场景演化与验证假设。
LLM智能体模拟虽能快速构建自然语言社会场景，但其输出常被误作预测，且难以与明确的社会动态进行比较。我们提出AgoraSim，一种面向场景的社会反应分析混合智能体建模框架。该框架将文本或多媒体内容解析为可编辑的智能体建模配置，支持混合比例控制的种群，包含大模型、视觉-语言、自定义端点、随机及经典智能体；可在相同场景下与匹配的经典参考动力学进行对比。所有智能体输出统一结构化决策对象，实现共享行动空间、交互协议、评估指标与审计记录。通过本地UI、Python SDK/CLI和REST API开放，AgoraSim帮助用户检查场景轨迹、比较建模假设，并识别需实证验证的案例。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。