LiveSim：在多智能体直播生态系统中模拟环境塑造的用户
LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
浏览论文内容
中文总结 AI 辅助
该研究提出基于LLM的LiveSim框架，通过环境塑造的动态用户行为模拟，在真实直播风控数据实验中验证其可提升用户级行为保真度并支持生态系统级分析。
中文摘要 AI 辅助
基于大语言模型（LLM）的用户行为模拟正越来越多地用于支持多智能体生态系统模拟。现有模拟器通常依赖从历史观测中推断出的静态用户画像，这在直播等社交密集型环境中并不适用，此类环境中互动动态会持续重塑用户行为。我们提出LiveSim，一个基于LLM的直播生态系统模拟框架。该框架将用户表示为可编辑的行为假设，并通过基于轨迹的互动逐步优化这些假设，其中模拟轨迹与观测轨迹之间的差异会揭示缺失的环境塑造效应。这些信号被进一步提取为可迁移的环境-行为模式，并累积在集体行为记忆中，以提高用户级行为保真度并支持生态系统级模拟。对真实世界直播风控数据的实验验证了LiveSim在提高用户级行为保真度、实现风险演化的生态系统级分析以及平台干预效果方面的有效性。
英文摘要
User behavior simulation with large language models~(LLMs) is increasingly used to support multi-agent ecosystem simulation. Existing simulators typically rely on static user profiles inferred from historical observations, which become inadequate in socially intensive environments such as live streaming where interaction dynamics continuously reshape user behavior. We propose \textbf{LiveSim}, an LLM-based framework for live-stream ecosystem simulation. It represents users as editable behavioral hypotheses and progressively refines them through trajectory-grounded interactions, where discrepancies between simulated and observed trajectories reveal missing environmental shaping effects. These signals are further extracted as transferable environment-behavior patterns and accumulated in a collective behavioral memory to improve user-level behavioral fidelity and support ecosystem-level simulation. Experiments on real-world live-stream risk-control data validate the effectiveness of LiveSim in improving user-level behavioral fidelity and enabling ecosystem-level analysis of risk evolution and platform intervention effects.
发表机构
- University of Chinese Academy of Sciences（中国科学院大学）
- ByteDance China（字节跳动中国）
机构由 AI 辅助整理，请以论文原文为准。
