VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks

TL;DR

VisualWebArena is a new benchmark for evaluating multimodal web agents on realistic visual tasks, highlighting current limitations and guiding future improvements in multimodal autonomous web agents.

Contribution

Introduces VisualWebArena, a benchmark for assessing multimodal web agents on complex visual tasks, filling a gap in existing text-only web automation benchmarks.

Findings

Text-only agents have significant limitations on visual tasks.

Multimodal models show improved performance but still have notable gaps.

Benchmark reveals specific challenges in processing image-text inputs and executing web actions.

Abstract

Autonomous agents capable of planning, reasoning, and executing actions on the web offer a promising avenue for automating computer tasks. However, the majority of existing benchmarks primarily focus on text-based agents, neglecting many natural tasks that require visual information to effectively solve. Given that most computer interfaces cater to human perception, visual information often augments textual data in ways that text-only models struggle to harness effectively. To bridge this gap, we introduce VisualWebArena, a benchmark designed to assess the performance of multimodal web agents on realistic \textit{visually grounded tasks}. VisualWebArena comprises of a set of diverse and complex web-based tasks that evaluate various capabilities of autonomous multimodal agents. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives. We conduct an extensive evaluation of state-of-the-art LLM-based autonomous agents, including several multimodal models. Through extensive quantitative and qualitative analysis, we identify several limitations of text-only LLM agents, and reveal gaps in the capabilities of state-of-the-art multimodal language agents. VisualWebArena provides a framework for evaluating multimodal autonomous language agents, and offers insights towards building stronger autonomous agents for the web. Our code, baseline models, and data is publicly available at https://jykoh.com/vwa.