# GuideWeb: A Benchmark for Automatic In-App Guide Generation on Real-World Web UIs

arXiv: https://arxiv.org/abs/2602.01917 · HTML: https://mlsanity.com/paper/2602.01917/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models](https://mlsanity.com/paper/2503.23350/) (2025)
- [HelpViz: Automatic Generation of Contextual Visual MobileTutorials from Text-Based Instructions](https://mlsanity.com/paper/2108.03356/) (2021)

## Built on by (most cited first, 2 of 2)

- [RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management](https://mlsanity.com/paper/2604.13531/) (2026)
- [MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation](https://mlsanity.com/paper/2607.10079/) (2026)

## Abstract (arXiv)

Digital Adoption Platform (DAP) provide web-based overlays that deliver operation guidance and contextual hints to help users navigate complex websites. Although modern DAP tools enable non-experts to author such guidance, maintaining these guides remains labor-intensive because website layouts and functionalities evolve continuously, which requires repeated manual updates and re-annotation. In this work, we introduce GuideWeb, a new benchmark for automatic in-app guide generation on real-world web UIs. GuideWeb formulates the task as producing page-level guidance by selecting guide target elements grounded in the webpage and generating concise guide text aligned with user intent. We also propose a comprehensive evaluation suite that jointly measures the accuracy of guide target element selection and the quality of generated intents and guide texts. Experiments show that our proposed GuideWeb Agent achieves 30.79% accuracy in guide target element prediction, while obtaining BLEU scores of 44.94 for intent generation and 21.34 for guide-text generation. Existing baselines perform substantially worse, which highlights that automatic guide generation remains challenging and that further advances are necessary before such systems can be reliably deployed in real-world settings.