Information-seeking (IS) agents have achieved strong performance across a range of wide and deep search tasks, yet their tool use remains largely restricted to API-level snippet retrieval and URL-based page fetching, limiting access to the richer information available through real browsing. While full browser interaction could unlock deeper capabilities, its fine-grained control and verbose page content returns introduce substantial complexity for ReAct-style function-calling agents. To bridge this gap, we propose Nested Browser-Use Learning (NestBrowse), which introduces a minimal and complete browser-action framework that decouples interaction control from page exploration through a nested structure. This design simplifies agentic reasoning while enabling effective deep-web information acquisition. Empirical results on challenging deep IS benchmarks demonstrate that NestBrowse offers clear benefits in practice. Further in-depth analyses underscore its efficiency and flexibility.
@article{arxiv.2512.23647,
title = {Nested Browser-Use Learning for Agentic Information Seeking},
author = {Baixuan Li and Jialong Wu and Wenbiao Yin and Kuan Li and Zhongwang Zhang and Huifeng Yin and Zhengwei Tao and Liwen Zhang and Pengjun Xie and Jingren Zhou and Yong Jiang},
journal= {arXiv preprint arXiv:2512.23647},
year = {2025}
}