Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.13531 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911594677534720 |
|---|---|
| author | Chen, Renqi Tao, Zeyin Guo, Jianming Wang, Jing Xu, Zezhou Zhu, Jingzhe Sun, Qingqing Zhang, Tianyi Chen, Shuai |
| author_facet | Chen, Renqi Tao, Zeyin Guo, Jianming Wang, Jing Xu, Zezhou Zhu, Jingzhe Sun, Qingqing Zhang, Tianyi Chen, Shuai |
| contents | Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environments. Their effectiveness in high-stakes, investigative domains such as authentic e-commerce risk management remains underexplored. To bridge this gap, we present RiskWebWorld, the first highly realistic interactive benchmark for evaluating GUI agents in e-commerce risk management. RiskWebWorld features 1,513 tasks sourced from production risk-control pipelines across 8 core domains, and captures the authentic challenges of risk operations on uncooperative websites, partially environmental hijackments. To support scalable evaluation and agentic reinforcement learning (RL), we further build a Gymnasium-compliant infrastructure that decouples policy planning from environment mechanics. Our evaluation across diverse models reveals a dramatic capability gap: top-tier generalist models achieve 49.1% success, while specialized open-weights GUI models lag at near-total failure. This highlights that foundation model scale currently matters more than zero-shot interface grounding in long-horizon professional tasks. We also demonstrate the viability of our infrastructure through agentic RL, which improves open-source models by 16.2%. These results position RiskWebWorld as a practical testbed for developing robust digital workers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13531 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management Chen, Renqi Tao, Zeyin Guo, Jianming Wang, Jing Xu, Zezhou Zhu, Jingzhe Sun, Qingqing Zhang, Tianyi Chen, Shuai Artificial Intelligence Machine Learning Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environments. Their effectiveness in high-stakes, investigative domains such as authentic e-commerce risk management remains underexplored. To bridge this gap, we present RiskWebWorld, the first highly realistic interactive benchmark for evaluating GUI agents in e-commerce risk management. RiskWebWorld features 1,513 tasks sourced from production risk-control pipelines across 8 core domains, and captures the authentic challenges of risk operations on uncooperative websites, partially environmental hijackments. To support scalable evaluation and agentic reinforcement learning (RL), we further build a Gymnasium-compliant infrastructure that decouples policy planning from environment mechanics. Our evaluation across diverse models reveals a dramatic capability gap: top-tier generalist models achieve 49.1% success, while specialized open-weights GUI models lag at near-total failure. This highlights that foundation model scale currently matters more than zero-shot interface grounding in long-horizon professional tasks. We also demonstrate the viability of our infrastructure through agentic RL, which improves open-source models by 16.2%. These results position RiskWebWorld as a practical testbed for developing robust digital workers. |
| title | RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.13531 |