Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms

Haoting Zhang, Yunduan Lin, Jinghai He, Denglin Jiang, Zuo-Jun, Shen, Zeyu Zheng

TL;DR

A large language model-augmented digital twin for short-video platforms, with a modular four-twin architecture and an event-driven execution layer that supports reproducible experimentation, enabling the study of platform policies, including AI-enabled policies, under realistic feedback and constraints.

Abstract

Short-video platforms are closed-loop, human-in-the-loop ecosystems where platform policy, creator incentives, and user behavior co-evolve. This feedback structure makes counterfactual policy evaluation difficult in production, especially for long-horizon and distributional outcomes. The challenge is amplified as platforms deploy AI tools that change what content enters the system, how agents adapt, and how the platform operates. We propose a large language model (LLM)-augmented digital twin for short-video platforms, with a modular four-twin architecture (User, Content, Interaction, Platform) and an event-driven execution layer that supports reproducible experimentation. Platform policies are implemented as pluggable components within the Platform Twin, and LLMs are integrated as optional, schema-constrained decision services (e.g., persona generation, content captioning, campaign planning, trend prediction) that are routed through a unified optimizer. This design enables scalable simulations that preserve closed-loop dynamics while allowing selective LLM adoption, enabling the study of platform policies, including AI-enabled policies, under realistic feedback and constraints.

LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms

TL;DR

A large language model-augmented digital twin for short-video platforms, with a modular four-twin architecture and an event-driven execution layer that supports reproducible experimentation, enabling the study of platform policies, including AI-enabled policies, under realistic feedback and constraints.

Abstract

Short-video platforms are closed-loop, human-in-the-loop ecosystems where platform policy, creator incentives, and user behavior co-evolve. This feedback structure makes counterfactual policy evaluation difficult in production, especially for long-horizon and distributional outcomes. The challenge is amplified as platforms deploy AI tools that change what content enters the system, how agents adapt, and how the platform operates. We propose a large language model (LLM)-augmented digital twin for short-video platforms, with a modular four-twin architecture (User, Content, Interaction, Platform) and an event-driven execution layer that supports reproducible experimentation. Platform policies are implemented as pluggable components within the Platform Twin, and LLMs are integrated as optional, schema-constrained decision services (e.g., persona generation, content captioning, campaign planning, trend prediction) that are routed through a unified optimizer. This design enables scalable simulations that preserve closed-loop dynamics while allowing selective LLM adoption, enabling the study of platform policies, including AI-enabled policies, under realistic feedback and constraints.
Paper Structure (48 sections, 1 equation, 4 figures, 5 tables)

This paper contains 48 sections, 1 equation, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Short-Video Platform and Policy Evaluation
  4. LLM sandbox
  5. System Description
  6. Four-Twin Architecture
  7. Event System and Environment Orchestrator
  8. Workflow: Content consumption.
  9. Large Language Model Integration and Cost Governance
  10. Experiments and Evaluation
  11. Experimental Setup.
  12. LLM Role.
  13. Experiment Set 1: LLM Creator Campaign Planning
  14. Design.
  15. Results.
  16. ...and 33 more sections

Figures (4)

  • Figure 1: Illustration of Four-Twin Architecture
  • Figure 3: Distribution of creator earnings. The simulation reproduces a heavy-tailed income distribution in which a small fraction of creators capture most revenue. The LLM planner (green) shifts density modestly toward the center relative to the heuristic baseline (grey), consistent with the reduction in Gift-Gini (0.62$\rightarrow$0.58).
  • Figure 4: Ecosystem effects of LLM Planner adoption. As the adoption rate of the strategic planner increases from 0% to 100%, we observe a clear decrease in income inequality (Gini coefficient, red line, left axis). Total ecosystem revenue shows a modest, non-monotonic increase (blue dashed line, right axis). This suggests that widespread access to optimization tools can democratize performance without harming the overall platform economy.
  • Figure 5: Trend Lifecycle and Forecasting. The solid line tracks the trend score of a viral hashtag (e.g., #sustainable_living) over time, driven by user interaction volume (grey bars). The dashed line represents the LLM-generated forecast issued during the emergence phase, demonstrating the Platform Twin's ability to anticipate viral peaks before they occur.