Nested Browser-Use Learning for Agentic Information Seeking

TL;DR

NestBrowse introduces a nested browser-action framework that simplifies agentic reasoning for deep web information seeking, enabling more effective and flexible browser interactions beyond API-level retrieval.

Contribution

It proposes a minimal, complete nested browser-action framework that decouples interaction control from page exploration, improving deep web information acquisition.

Findings

Outperforms existing methods on deep information-seeking benchmarks.

Demonstrates increased efficiency and flexibility in browser-based agents.

Enables richer information access through a simplified interaction model.

Abstract

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.