---
title: 'WebArena: A Realistic Web Environment for Building Autonomous Agents'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'This note is CC BY 4.0. It links to the paper and does not reproduce it. Paper license: arXiv non-exclusive distribution (verified on arXiv abs page 2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/).'
source: https://iinventedlight.com/library/notes/2307-13854-webarena.md
source_license: 'arXiv default (non-exclusive distribution license)'
attribution: 'Pointer note by iinventedlight (AI-assisted). Links to: Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, et al. (12 authors), WebArena: A Realistic Web Environment for Building Autonomous Agents (arXiv). This note does not reproduce the paper.'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-11
status: published
approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\""
checked_on: 2026-11-11
as_of: 2026-11-11
confidence: medium
untested: 'Pointer note only. Abs page read 2026-11-11. The paper is not reproduced here.'
category: arxiv
topic_area: 'ai-research: agents'
tags: arxiv, pointer, agents
arxiv_id: 2307.13854
alias: 2307.13854-webarena
format: pointer
type: pointer
sources:
  - id: S1
    title: 'WebArena: A Realistic Web Environment for Building Autonomous Agents'
    publisher: arXiv
    authors: 'Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, et al. (12 authors)'
    url: https://arxiv.org/abs/2307.13854
    version_read: 'v4 (16 Apr 2024)'
    accessed: 2026-11-11
    license: 'arXiv default (non-exclusive distribution license)'
---
# WebArena: A Realistic Web Environment for Building Autonomous Agents

## Summary
WebArena: A Realistic Web Environment for Building Autonomous Agents (2023), by Shuyan Zhou, Frank F. Xu, Hao Zhu, and coauthors, is at https://arxiv.org/abs/2307.13854. The authors build fully functional sites in four domains: e-commerce, social forum discussions, collaborative software development, and content management, and they add tools such as a map and external knowledge bases such as user manuals. They release a set of benchmark tasks focusing on evaluating the functional correctness of task completions. In their experiments, including agents that reason before acting, the best GPT-4-based agent reached an end-to-end success rate of 14.41%, far below the reported human performance of 78.24%. Code, data, and environment resources are pointed to https://webarena.dev/. They experiment with several baseline agents, integrating recent techniques such as reasoning before acting. Their best GPT 4 based agent only achieves an end-to-end task success rate of 14.41%, significantly lower than the human performance of 78.24%. They say these results highlight the need for further development of robust agents. Title, authors, abstract, and comments were taken from the arXiv abs page. The version is v4 (16 Apr 2024), submitted 25 Jul 2023.

## Claims
Pointer notes do not quote the paper. See Verification and Sources for the link and license.

## Verification
- Format: pointer note only. The paper is not reproduced here.
- Why it matters: It matters because it gave the field a realistic, self-hosted website environment instead of a thin mock browser.
- Reproduced: not reproduced (2026-11-11).
- Related work: Related notes already in the library include [Evaluating multimodal agents](https://iinventedlight.com/library/notes/ao-evals-multimodal-agents/) and [ReAct](https://iinventedlight.com/library/notes/2210-03629-react-reasoning-and-acting/).
- Limits: This is a pointer note only. The 14.41% versus 78.24% figures are the authors' reported GPT-4 agent versus human results from the v4 paper (16 Apr 2024).
- License: arXiv default (non-exclusive distribution license) on the abs page (2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/). Submitted 25 Jul 2023 (v1); last revised 16 Apr 2024 (v4). Sources: [S1] https://arxiv.org/abs/2307.13854, v4 (16 Apr 2024). checked_on: 2026-11-11. Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it. The note itself is CC BY 4.0.

## When to apply
Use when you need the original WebArena paper for realistic, self-hosted web-agent evaluation.

## Facts
- id: F1
  claim: 'WebArena is a reproducible web environment with fully functional websites in four domains: e-commerce, social forum discussions, collaborative software development, and content management.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0
- id: F2
  claim: 'The authors report that their best GPT-4-based agent achieved an end-to-end task success rate of 14.41%, compared with human performance of 78.24%.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0
- id: F3
  claim: 'They point to public code, data, and environment resources at https://webarena.dev/.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC-BY-4.0

## Sources
- [S1] arXiv 2307.13854, https://arxiv.org/abs/2307.13854. Paper license: arXiv default (non-exclusive distribution license). v4 (16 Apr 2024). Accessed 2026-11-11. This note links to the paper and does not reproduce it.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).