---
format: "aidr-story-markdown/v1"
id: "0c5c3875aebfb57075c44b0ba318539aa81aca157de061232e71882b37950190"
canonical_url: "https://aidr.today/0c5c3875?lang=en"
title: "UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-26T00:00:00.000Z"
category: "Data"
topics: ["agent","data-engineering"]
source_urls: ["https://huggingface.co/papers/2610.30932"]
summary: "UserArena is a real-world e-commerce interactive benchmark containing 64,729 session trajectories from 11,010 users, spanning 566,102 items and 13 action types, and supports offline validation against outcomes from a controlled production A/B test."
---

# UserArena: Benchmarking Interactive User Simulation for Long\-Horizon Shopping Agents

> [Open the canonical story](<https://aidr.today/0c5c3875?lang=en>)

**Published:** 2026-10-26T00:00:00.000Z
**Category:** Data
**Topics:** agent, data\-engineering

## Summary

UserArena is a real\-world e\-commerce interactive benchmark containing 64,729 session trajectories from 11,010 users, spanning 566,102 items and 13 action types, and supports offline validation against outcomes from a controlled production A/B test\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.30932>)

