---
format: "aidr-story-markdown/v1"
id: "8e856ecf4cf11072b5b8f3ef0d8df099041a29ca0d81be8c5cd0a1a955c51f6c"
canonical_url: "https://aidr.today/8e856ecf?lang=en"
title: "MemU-Bench: Benchmarking GUI Agents on Long-Horizon User Interactions"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-03T05:00:00.000Z"
category: "Research"
topics: ["agent"]
source_urls: ["https://arxiv.org/abs/2611.00191"]
summary: "Existing Graphical User Interface (GUI) benchmarks predominantly rely on precise and stateless user instructions. In everyday usage, however, instructions are often \\emph{vague and history-dependent}: users omit the exact details of their past operations because they no longer remember them, leaving the agent to recover the missing context from long and noisy interaction histories. To bridge this evaluation gap, we introduce \\textbf{MemU-Bench}, a mobile benchmark of \\textbf{118 vague tasks} grounded in 29 long-horizon user trajectories, where agents must distill raw interaction streams into memory and retrieve the missing context on demand, with task outcomes verified against serialized application databases. Alongside Success Rate, we incorporate Interaction Efficiency (IE) and Success weighted by Path Length (SPL) to expose agents that succeed by exhaustively searching across different applications rather than by \\emph{genuinely recalling} the history."
---

# MemU\-Bench: Benchmarking GUI Agents on Long\-Horizon User Interactions

> [Open the canonical story](<https://aidr.today/8e856ecf?lang=en>)

**Published:** 2026-11-03T05:00:00.000Z
**Category:** Research
**Topics:** agent

## Summary

Existing Graphical User Interface \(GUI\) benchmarks predominantly rely on precise and stateless user instructions\. In everyday usage, however, instructions are often \\emph\{vague and history\-dependent\}: users omit the exact details of their past operations because they no longer remember them, leaving the agent to recover the missing context from long and noisy interaction histories\. To bridge this evaluation gap, we introduce \\textbf\{MemU\-Bench\}, a mobile benchmark of \\textbf\{118 vague tasks\} grounded in 29 long\-horizon user trajectories, where agents must distill raw interaction streams into memory and retrieve the missing context on demand, with task outcomes verified against serialized application databases\. Alongside Success Rate, we incorporate Interaction Efficiency \(IE\) and Success weighted by Path Length \(SPL\) to expose agents that succeed by exhaustively searching across different applications rather than by \\emph\{genuinely recalling\} the history\.

## Sources

- [Story source](<https://arxiv.org/abs/2611.00191>)