Spokes.wiki Search About
Scholarly Article source ↗ source url updated Sun Aug 09 2026 00:00:00 GMT+0000 (Coordinated Universal Time)

WebArena

Zhou, Xu, Zhu, Zhou, Lo, Sridhar, Cheng, Ou, Bisk, Fried, Alon and Neubig (CMU), WebArena: A Realistic Web Environment for Building Autonomous Agents, 2023 (revised 2024). T1.

A self-hosted, reproducible environment of real web applications rather than a mock: e-commerce, a social forum, collaborative software development (a GitLab instance), and content management, plus supporting tools like maps and a knowledge base. The motivation is stated as a complaint about the field — agents “are primarily created and tested in simplified synthetic environments, leading to a disconnect with real-world scenarios.”

Tasks are graded on functional correctness: did the intended state change happen, not did the trajectory look right.

The headline gap: a GPT-4-based agent reached 14.41% end-to-end success where humans reached 78.24%. Published in 2023, so the absolute numbers are stale — the shape is not, and it is the reason this spoke’s browser-agent claims deserve a benchmark citation rather than a demo.

What it adds to the spoke’s evaluation set

Three benchmarks, three different failure surfaces:

taskenvironmentwhat fails
swe-benchfix a real GitHub issuerepository + testsreasoning across files
tau-benchserve a user under policyAPIs + simulated userconsistency (pass^k)
WebArenaoperate real web appslive self-hosted siteslong horizons, UI state, recovery

WebArena is the one that measures acting in an environment nobody designed for an agent — no clean tool schema, just pages. That is also why it is the natural benchmark for the browser-agent claims tracked in ../web-browsers-wiki, where vendors report their own numbers on their own harnesses.

Not held here: BrowserGym, which coverage edge 7 also named, and any post-2024 re-run of WebArena.