Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

TL;DR

Mind2Web 2 introduces a comprehensive benchmark and a novel evaluation framework for agentic web search systems, enabling assessment of complex, long-horizon tasks and real-time answer accuracy, which advances the development of autonomous information retrieval agents.

Contribution

The paper presents Mind2Web 2, a large-scale benchmark of long-horizon tasks and an Agent-as-a-Judge evaluation framework for assessing complex agentic search systems.

Findings

OpenAI Deep Research achieves 50-70% of human performance.

The benchmark includes 130 tasks with over 1000 hours of human labor.

The evaluation framework effectively assesses answer correctness and source attribution.

Abstract

Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how users interact with web-scale information. While promising greater efficiency and cognitive offloading, the growing complexity and open-endedness of agentic search have outpaced existing evaluation benchmarks and methodologies, which largely assume short search horizons and static answers. In this paper, we introduce Mind2Web 2, a benchmark of 130 realistic, high-quality, and long-horizon tasks that require real-time web browsing and extensive information synthesis, constructed with over 1000 hours of human labor. To address the challenge of evaluating time-varying and complex answers, we propose a novel Agent-as-a-Judge framework. Our method constructs task-specific judge agents based on a tree-structured rubric design to automatically assess both answer correctness and source attribution. We conduct a comprehensive evaluation of ten frontier agentic search systems and human performance, along with a detailed error analysis to draw insights for future development. The best-performing system, OpenAI Deep Research, can already achieve 50-70% of human performance while spending half the time, highlighting its great potential. Altogether, Mind2Web 2 provides a rigorous foundation for developing and benchmarking the next generation of agentic search systems.