Search papers, labs, and topics across Lattice.
This paper introduces LiveSim, an innovative framework that utilizes large language models to simulate user behavior in dynamic live-streaming environments. By representing users as editable behavioral hypotheses and refining them through trajectory-grounded interactions, LiveSim addresses the limitations of traditional simulators that rely on static user profiles. Experiments demonstrate that LiveSim significantly enhances user-level behavioral fidelity and facilitates ecosystem-level analysis of risk evolution and intervention effects in real-world scenarios.
LiveSim transforms user behavior simulation by dynamically adapting to the evolving interactions in live-streaming environments, leading to unprecedented accuracy in risk analysis.
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.
DAMO