EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments
This addresses the need for rigorous evaluation of autonomous agents on economic tasks in realistic web settings, though it is incremental as it builds on existing web agent benchmarking.
The authors introduced EconWebArena, a benchmark with 360 tasks from 82 authoritative websites to evaluate autonomous agents on complex economic tasks in realistic web environments, revealing substantial performance gaps and persistent challenges in grounding, navigation, and multimodal understanding.
We introduce EconWebArena, a benchmark for evaluating autonomous agents on complex, multimodal economic tasks in realistic web environments. The benchmark comprises 360 curated tasks from 82 authoritative websites spanning domains such as macroeconomics, labor, finance, trade, and public policy. Each task challenges agents to navigate live websites, interpret structured and visual content, interact with real interfaces, and extract precise, time-sensitive data through multi-step workflows. We construct the benchmark by prompting multiple large language models (LLMs) to generate candidate tasks, followed by rigorous human curation to ensure clarity, feasibility, and source reliability. Unlike prior work, EconWebArena emphasizes fidelity to authoritative data sources and the need for grounded web-based economic reasoning. We evaluate a diverse set of state-of-the-art multimodal LLMs as web agents, analyze failure cases, and conduct ablation studies to assess the impact of visual grounding, plan-based reasoning, and interaction design. Our results reveal substantial performance gaps and highlight persistent challenges in grounding, navigation, and multimodal understanding, positioning EconWebArena as a rigorous testbed for economic web intelligence.