Mango: Multi-Agent Web Navigation via Global-View Optimization
Year: 2026
Type: preprint
Abstract: Existing web agents typically initiate exploration from the root URL, which is inefficient for complex websites with deep hierarchical structures. Without a global view of the website's structure, agents frequently fall into navigation traps, explore irrelevant branches, or fail to reach target information within a limited budget. We propose Mango, a multi-agent web navigation method that leverages the website structure to dynamically determine optimal starting points. We formulate URL selection as a multi-armed bandit problem and employ Thompson Sampling to adaptively allocate the navigation budget across candidate URLs. Furthermore, we introduce an episodic memory component to store navigation history, enabling the agent to learn from previous attempts. Experiments on WebVoyager demonstrate that Mango achieves a success rate of 63.6% when using GPT-5-mini, outperforming the best baseline by 7.3%. Furthermore, on WebWalkerQA, Mango attains a 52.5% success rate, surpassing the best baseline by 26.8%. We also demonstrate the generalizability of Mango using both open-source and closed-source models as backbones. Our data and code are open-source and available at https://github.com/VichyTong/Mango.
Source: arXiv (Cornell University)
Authors: Tong, Weixi, Di, Yifeng, Zhang, Tianyi
Institution: Purdue University West Lafayette
Topic: Web Data Mining and Analysis
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7155211531
Cites:
Cited by:
Related to: