EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments

TL;DR

EconWebArena is a comprehensive benchmark for testing autonomous agents on complex economic tasks within realistic web environments, emphasizing multimodal reasoning and real-world data fidelity.

Contribution

The paper introduces a new benchmark with 360 tasks from authoritative sources, focusing on economic reasoning and web interaction, generated via LLMs and human curation.

Findings

State-of-the-art multimodal LLMs show significant performance gaps.

Visual grounding and web navigation remain challenging for current models.

Ablation studies highlight the importance of reasoning and interaction design.

Abstract

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.