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

arXiv: https://arxiv.org/abs/2603.11333 · HTML: https://mlsanity.com/paper/2603.11333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [AgentScope: A Flexible yet Robust Multi-Agent Platform](https://mlsanity.com/paper/2402.14034/) (2024)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [Emergence of Social Norms in Generative Agent Societies: Principles and Architecture](https://mlsanity.com/paper/2403.08251/) (2024)
- [Experimental Design in Two-Sided Platforms: An Analysis of Bias](https://mlsanity.com/paper/2002.05670/) (2020)
- [Design and Analysis of Switchback Experiments](https://mlsanity.com/paper/2009.00148/) (2020)
- [Optimal Experimental Design for Staggered Rollouts](https://mlsanity.com/paper/1911.03764/) (2019)
- [A/B Testing for Recommender Systems in a Two-sided Marketplace](https://mlsanity.com/paper/2106.00762/) (2021)
- [Unbiased Comparative Evaluation of Ranking Functions](https://mlsanity.com/paper/1604.07209/) (2016)
- [Collaborative Intelligence in Sequential Experiments: A Human-in-the-Loop Framework for Drug Discovery](https://mlsanity.com/paper/2405.03942/) (2024)
- [Daily Physical Activity Monitoring -- Adaptive Learning from Multi-source Motion Sensor Data](https://mlsanity.com/paper/2405.16395/) (2024)
- [Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information](https://mlsanity.com/paper/2501.17992/) (2025)
- [Causal inference with Machine Learning-Based Covariate Representation](https://mlsanity.com/paper/2311.01709/) (2023)

## Abstract (arXiv)

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.