# PAARS: Persona Aligned Agentic Retail Shoppers

arXiv: https://arxiv.org/abs/2503.24228 · HTML: https://mlsanity.com/paper/2503.24228/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.09738/) (2024)
- ["Global is Good, Local is Bad?": Understanding Brand Bias in LLMs](https://mlsanity.com/paper/2406.13997/) (2024)

## Built on by (most cited first, 15 of 15)

- [DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas](https://mlsanity.com/paper/2511.07338/) (2025)
- [A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments](https://mlsanity.com/paper/2509.25609/) (2025)
- [ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders](https://mlsanity.com/paper/2602.16938/) (2026)
- [In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations](https://mlsanity.com/paper/2602.15456/) (2026)
- [SimGym: Traffic-Grounded Browser Agents for Offline A/B Testing in E-Commerce](https://mlsanity.com/paper/2602.01443/) (2026)
- [PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM](https://mlsanity.com/paper/2511.17467/) (2025)
- [What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents](https://mlsanity.com/paper/2604.04468/) (2026)
- [SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents](https://mlsanity.com/paper/2605.19219/) (2026)
- [Data-Driven Persona-Conditioned Agents for A/B Test Simulation](https://mlsanity.com/paper/2609.01038/) (2026)
- [The Narcissus Hypothesis: Descending to the Rung of Illusion](https://mlsanity.com/paper/2509.17999/) (2025)
- [Evaluating the Effectiveness of Persona Simulation in Opinion Prediction with GPT-4.1](https://mlsanity.com/paper/2607.20589/) (2026)
- [Can AI Agents Simulate A/B Test Outcomes? A Validation Framework for Agentic Experimentation](https://mlsanity.com/paper/2608.02345/) (2026)
- [Augmented Hypothesis Testing with Persona-Based LLM Simulations](https://mlsanity.com/paper/2609.24629/) (2026)
- [SimTrace: Grounded Multimodal User Trajectories Generation for Online User Modeling](https://mlsanity.com/paper/2609.38397/) (2026)
- [Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes](https://mlsanity.com/paper/2610.05828/) (2026)

## Abstract (arXiv)

In e-commerce, behavioral data is collected for decision making which can be costly and slow. Simulation with LLM powered agents is emerging as a promising alternative for representing human population behavior. However, LLMs are known to exhibit certain biases, such as brand bias, review rating bias and limited representation of certain groups in the population, hence they need to be carefully benchmarked and aligned to user behavior. Ultimately, our goal is to synthesise an agent population and verify that it collectively approximates a real sample of humans. To this end, we propose a framework that: (i) creates synthetic shopping agents by automatically mining personas from anonymised historical shopping data, (ii) equips agents with retail-specific tools to synthesise shopping sessions and (iii) introduces a novel alignment suite measuring distributional differences between humans and shopping agents at the group (i.e. population) level rather than the traditional "individual" level. Experimental results demonstrate that using personas improves performance on the alignment suite, though a gap remains to human behaviour. We showcase an initial application of our framework for automated agentic A/B testing and compare the findings to human results. Finally, we discuss applications, limitations and challenges setting the stage for impactful future work.