# PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing

arXiv: https://arxiv.org/abs/2601.22547 · HTML: https://mlsanity.com/paper/2601.22547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [User Behavior Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2306.02552/) (2023)
- [RecSim: A Configurable Simulation Platform for Recommender Systems](https://mlsanity.com/paper/1909.04847/) (2019)
- [Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning](https://mlsanity.com/paper/1805.10000/) (2018)
- [LLM-Powered User Simulator for Recommender System](https://mlsanity.com/paper/2412.16984/) (2024)
- [SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation](https://mlsanity.com/paper/2504.12722/) (2025)
- [Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shopping](https://mlsanity.com/paper/2510.07230/) (2025)
- [Revisiting Algorithmic Audits of TikTok: Poor Reproducibility and Short-term Validity of Findings](https://mlsanity.com/paper/2504.18140/) (2025)
- [Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation](https://mlsanity.com/paper/2512.03067/) (2025)

## Abstract (arXiv)

Short-video platforms rely on personalized recommendation, raising concerns about filter bubbles that narrow content exposure. Auditing such phenomena at scale is challenging because real user studies are costly and privacy-sensitive, and existing simulators fail to reproduce realistic behaviors due to their reliance on textual signals and weak personalization. We propose PersonaAct, a framework for simulating short-video users with persona-conditioned multimodal agents trained on real behavioral traces for auditing filter bubbles in breadth and depth. PersonaAct synthesizes interpretable personas through automated interviews combining behavioral analysis with structured questioning, then trains agents on multimodal observations using supervised fine-tuning and reinforcement learning. We deploy trained agents for filter bubble auditing and evaluate bubble breadth via content diversity and bubble depth via escape potential. The evaluation demonstrates substantial improvements in fidelity over generic LLM baselines, enabling realistic behavior reproduction. Results reveal significant content narrowing over interaction. However, we find that Bilibili demonstrates the strongest escape potential. We release the first open multimodal short-video dataset and code to support reproducible auditing of recommender systems.