# Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents

arXiv: https://arxiv.org/abs/2504.08742 · HTML: https://mlsanity.com/paper/2504.08742/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 45 references that are in the map.
- First posted on arXiv 23 Mar 2025.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 21 of 21)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities](https://mlsanity.com/paper/2310.10436/) (2023)
- [War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars](https://mlsanity.com/paper/2311.17227/) (2023)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [Feedback Loop and Bias Amplification in Recommender Systems](https://mlsanity.com/paper/2007.13019/) (2020)
- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [Embodied LLM Agents Learn to Cooperate in Organized Teams](https://mlsanity.com/paper/2403.12482/) (2024)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation](https://mlsanity.com/paper/2402.14978/) (2024)
- [Understanding Echo Chambers in E-commerce Recommender Systems](https://mlsanity.com/paper/2007.02474/) (2020)
- [DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation](https://mlsanity.com/paper/2211.10486/) (2022)
- [RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents](https://mlsanity.com/paper/2308.09904/) (2023)
- [DGCN: Diversified Recommendation with Graph Convolutional Networks](https://mlsanity.com/paper/2108.06952/) (2021)
- [PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning](https://mlsanity.com/paper/2403.14227/) (2024)
- [Modelling Political Coalition Negotiations Using LLM-based Agents](https://mlsanity.com/paper/2402.11712/) (2024)
- [Social-LLM: Modeling User Behavior at Scale using Language Models and Social Network Data](https://mlsanity.com/paper/2401.00893/) (2023)
- [On Practical Diversified Recommendation with Controllable Category Diversity Framework](https://mlsanity.com/paper/2402.03801/) (2024)
- [Filter bubbles and affective polarization in user-personalized large language model outputs](https://mlsanity.com/paper/2311.14677/) (2023)

## Built on by (most cited first, 1 of 1)

- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)

## Abstract (arXiv)

An increasing reliance on recommender systems has led to concerns about the creation of filter bubbles on social media, especially on short video platforms like TikTok. However, their formation is still not entirely understood due to the complex dynamics between recommendation algorithms and user feedback. In this paper, we aim to shed light on these dynamics using a large language model-based simulation framework. Our work employs real-world short-video data containing rich video content information and detailed user-agents to realistically simulate the recommendation-feedback cycle. Through large-scale simulations, we demonstrate that LLMs can replicate real-world user-recommender interactions, uncovering key mechanisms driving filter bubble formation. We identify critical factors, such as demographic features and category attraction that exacerbate content homogenization. To mitigate this, we design and test interventions including various cold-start and feedback weighting strategies, showing measurable reductions in filter bubble effects. Our framework enables rapid prototyping of recommendation strategies, offering actionable solutions to enhance content diversity in real-world systems. Furthermore, we analyze how LLM-inherent biases may propagate through recommendations, proposing safeguards to promote equity for vulnerable groups, such as women and low-income populations. By examining the interplay between recommendation and LLM agents, this work advances a deeper understanding of algorithmic bias and provides practical tools to promote inclusive digital spaces.