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

TL;DR

This paper introduces an LLM-augmented digital twin framework for short-video platforms, enabling scalable, realistic policy evaluation with integrated AI tools in a closed-loop environment.

Contribution

It presents a modular four-twin architecture with an event-driven layer and pluggable LLM decision services for simulating and evaluating platform policies.

Findings

Supports reproducible experimentation with platform policies.

Allows integration of AI-enabled policies within the simulation.

Enables study of long-term and distributional effects of policies.

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.