Problem
Research questions and friction points this paper is trying to address.
User behavior simulation
multi-agent ecosystem
live streaming
environmental shaping effects
LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
🤖 AI Summary
为解决直播环境中用户行为模拟问题，提出LiveSim框架，通过LLM和交互轨迹逐步优化用户行为假设，提高用户级行为逼真度及生态系统级分析能力。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
LiveSim
LLM-based framework
editable behavioral hypotheses
trajectory-grounded interactions
environment-behavior patterns
🔎 Similar Papers
No similar papers found.
