@inproceedings{benomar-etal-2026-data,
title = "Data-Driven Persona-Conditioned Agents for A/{B} Test Simulation",
author = "Benomar, Ziyad and
{\L}ajewska, Weronika and
Perelli, Leonardo and
Mansour, Saab",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.79/",
pages = "1323--1338",
ISBN = "979-8-89176-460-6",
abstract = "A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propose a simulation framework that predicts A/B test outcomes using LLM-powered agents conditioned on data-driven personas grounded in real user behavioral signals. Unlike prior work that relies on synthetic or rule-based personas, our agents are constructed from anonymized behavioral data{---}activity patterns, engagement signals, and inferred demographics{---}enabling more faithful population modeling. We frame A/B test simulation as a structured question task and systematically study (i) question design formats, (ii) the impact of persona data source and domain alignment, (iii) the trade-off between per-persona behavioral depth and population diversity, and (iv) efficient population subsampling. On a benchmark of 40 A/B tests spanning two metric types, our best configuration achieves 0.75{--}0.90 directional accuracy depending on the test metric, demonstrating that data-driven personas are a viable path toward fast, low-cost experiment pre-screening."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="benomar-etal-2026-data">
<titleInfo>
<title>Data-Driven Persona-Conditioned Agents for A/B Test Simulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziyad</namePart>
<namePart type="family">Benomar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weronika</namePart>
<namePart type="family">Łajewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Perelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saab</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propose a simulation framework that predicts A/B test outcomes using LLM-powered agents conditioned on data-driven personas grounded in real user behavioral signals. Unlike prior work that relies on synthetic or rule-based personas, our agents are constructed from anonymized behavioral data—activity patterns, engagement signals, and inferred demographics—enabling more faithful population modeling. We frame A/B test simulation as a structured question task and systematically study (i) question design formats, (ii) the impact of persona data source and domain alignment, (iii) the trade-off between per-persona behavioral depth and population diversity, and (iv) efficient population subsampling. On a benchmark of 40 A/B tests spanning two metric types, our best configuration achieves 0.75–0.90 directional accuracy depending on the test metric, demonstrating that data-driven personas are a viable path toward fast, low-cost experiment pre-screening.</abstract>
<identifier type="citekey">benomar-etal-2026-data</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.79/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1323</start>
<end>1338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data-Driven Persona-Conditioned Agents for A/B Test Simulation
%A Benomar, Ziyad
%A Łajewska, Weronika
%A Perelli, Leonardo
%A Mansour, Saab
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F benomar-etal-2026-data
%X A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propose a simulation framework that predicts A/B test outcomes using LLM-powered agents conditioned on data-driven personas grounded in real user behavioral signals. Unlike prior work that relies on synthetic or rule-based personas, our agents are constructed from anonymized behavioral data—activity patterns, engagement signals, and inferred demographics—enabling more faithful population modeling. We frame A/B test simulation as a structured question task and systematically study (i) question design formats, (ii) the impact of persona data source and domain alignment, (iii) the trade-off between per-persona behavioral depth and population diversity, and (iv) efficient population subsampling. On a benchmark of 40 A/B tests spanning two metric types, our best configuration achieves 0.75–0.90 directional accuracy depending on the test metric, demonstrating that data-driven personas are a viable path toward fast, low-cost experiment pre-screening.
%U https://aclanthology.org/2026.emnlp-industry.79/
%P 1323-1338
Markdown (Informal)
[Data-Driven Persona-Conditioned Agents for A/B Test Simulation](https://aclanthology.org/2026.emnlp-industry.79/) (Benomar et al., EMNLP 2026)
ACL
- Ziyad Benomar, Weronika Łajewska, Leonardo Perelli, and Saab Mansour. 2026. Data-Driven Persona-Conditioned Agents for A/B Test Simulation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1323–1338, Budapest, Hungary. Association for Computational Linguistics.