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

• URL: http://arxiv.org/abs/2603.11333v1
• Date: Wed, 11 Mar 2026 21:50:21 GMT
• Title: LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms
• Abstract summary: Short-video platforms are closed-loop, human-in-the-loop ecosystems where policy, creator incentives, and user behavior co-evolve.<n>We propose a large language model (LLM)-augmented digital twin for short-video platforms with a modular four-twin architecture.
• Score: 12.693132563364342
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Partially Observable Learning for Multi-Platform Dispatch Optimization [2.877073407903913]
  In real-world systems, couriers are not exclusive to a single platform and may concurrently serve multiple platforms.<n>This results in a multi-platform dispatch environment with inherent partial observability.<n>We propose POLO, a partially observable multi-agent reinforcement learning framework for dispatching optimization in multi-platform instant delivery systems.
  arXiv  Detail & Related papers  (2026-08-11T13:20:12Z)
• UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning [67.45909103605858]
  We propose UI-MOPD, a method that incorporates multi-teacher on-policy distillation into continual learning for GUI agents.<n>Experiments on OSWorld and MobileWorld show that UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively.
  arXiv  Detail & Related papers  (2026-07-05T17:37:12Z)
• PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization [22.490419080772586]
  PolicySim is an LLM-based social simulation sandbox for the proactive assessment and optimization of intervention policies.<n>We show that PolicySim can accurately simulate platform ecosystems at both micro and macro levels.
  arXiv  Detail & Related papers  (2026-03-20T05:20:39Z)
• A Versatile Multimodal Agent for Multimedia Content Generation [66.86040734610073]
  We propose a MultiMedia-Agent designed to automate complex content creation tasks.<n>Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment.
  arXiv  Detail & Related papers  (2026-01-06T18:49:47Z)
• Review of Tools for Zero-Code LLM Based Application Development [0.6978180153516672]
  Large Language Models (LLMs) are transforming software creation by enabling zero code development platforms.<n>Our survey reviews recent platforms that let users build applications without writing code, by leveraging LLMs as the brains of the development process.
  arXiv  Detail & Related papers  (2025-10-22T16:41:16Z)
• Personalized Learning Path Planning with Goal-Driven Learner State Modeling [68.96987567845824]
  We introduce Pxplore, a novel framework for personalized learning paths.<n>We design a structured learner state model and an automated reward function that transforms abstract objectives into computable signals.<n>Experiments validate Pxplore's effectiveness in producing coherent, personalized, and goal-driven learning paths.
  arXiv  Detail & Related papers  (2025-10-15T06:59:49Z)
• LLM Chatbot-Creation Approaches [0.18374319565577157]
  This study compares two development approaches: low-code platforms like AnythingLLM and Botpress, with custom-coded solutions using LangChain, FAISS, and FastAPI.<n>Findings indicate that while low-code platforms enable rapid prototyping, they face limitations in customization and scaling, while custom-coded systems offer more control but require significant technical expertise.
  arXiv  Detail & Related papers  (2025-08-28T02:37:24Z)
• Navigation Pixie: Implementation and Empirical Study Toward On-demand Navigation Agents in Commercial Metaverse [3.05484549776329]
  We present Navigation Pixie, an on-demand navigation agent employing a loosely coupled architecture that integrates structured spatial metadata with natural language processing.<n>Our cross-platform experiments on commercial metaverse platform Cluster with 99 PC client and 94 VR-HMD participants demonstrated that Navigation Pixie significantly increased dwell time and free exploration.<n>This research contributes to advancing VR interaction design through conversational spatial navigation agents.
  arXiv  Detail & Related papers  (2025-08-05T08:45:34Z)
• Platform-Aware Mission Planning [50.56223680851687]
  We introduce the problem of Platform-Aware Mission Planning (PAMP), addressing it in the setting of temporal durative actions.<n>The first baseline approach amalgamates the mission and platform levels, while the second is based on an abstraction-refinement loop.<n>We prove the soundness and completeness of the proposed approaches and validate them experimentally.
  arXiv  Detail & Related papers  (2025-01-16T16:20:37Z)
• Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning [51.52387511006586]
  We propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies. HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios.
  arXiv  Detail & Related papers  (2024-06-12T08:48:06Z)
• LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins [31.678328189420483]
  Large language model (LLM) platforms have recently begun offering an app ecosystem to interface with third-party services on the internet. While these apps extend the capabilities of LLM platforms, they are developed by arbitrary third parties and thus cannot be implicitly trusted. We propose a framework that lays a foundation for LLM platform designers to analyze and improve the security, privacy, and safety of current and future third-party integrated LLM platforms.
  arXiv  Detail & Related papers  (2023-09-19T02:20:10Z)
• Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic [59.94347858883343]
  This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states.
  arXiv  Detail & Related papers  (2021-02-24T01:11:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.