LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
cs.AI, cs.CY, cs.MA
Submitted: 2026-08-27
Updated: 2026-08-31
Comments: 20 pages, 8 figures, 7 tables
License: http://creativecommons.org/licenses/by/4.0/
The gist: User behavior simulation with large language models (LLMs) is increasingly used to support multi-agent ecosystem simulation.
Terminology
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 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.
Sources
- Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization
- Profile-LLM: Dynamic Profile Optimization for Realistic Personality Expression in LLMs
- LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation
- Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
- From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
- Simulating Human-like Daily Activities with Desire-driven Autonomy
- OASIS: Open Agent Social Interaction Simulations with One Million Agents
- CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection