What capabilities does WorkArena test?

WorkArena evaluates browser use, tool calling, planning.

How can a model improve its WorkArena score?

Tools linked to WorkArena on Sophon include BrowserGym, Openenv Browsergym RL Env (Hugging Face) - RL environments, datasets, and scaffolds that target this eval.

What license is WorkArena under?

WorkArena is available under Apache-2.0.

WorkArena

Active

Browser-based enterprise web tasks on a live ServiceNow instance - list filtering, form filling, knowledge search - covering daily knowledge-worker workflows.

Open

Publisher: ServiceNow Research
Capabilities: Browser Use Tool Calling Planning
Domain: agentic
Format: Custom
Size: 682 tasks
License: Apache-2.0
Published: Mar 2024
Notable for: Benchmark for evaluating browser use, tool calling and planning in the agentic domain.
Canonical: github.com/ServiceNow/WorkArena
Also on: servicenow.github.io/WorkArena

Cite

Notes

Only stored in your browser.

Related tools

View all

Implementations, trainers, datasets and scaffolds linked to this eval.

BrowserGym

ServiceNow Research

ServiceNow's unified Gym-style framework for web agents - wraps WebArena, MiniWoB, VisualWebArena, WorkArena, AssistantBench, WebLINX, and more under one Playwright-backed interface.

Trains towardRL EnvPlanningTool CallingBrowser Use

Openenv Browsergym RL Env (Hugging Face)

Hugging Face

OpenEnv port of ServiceNow's BrowserGym - a Playwright-backed browser environment exposing WebArena, MiniWoB, WorkArena, etc. through the standard OpenEnv API.

Trains towardRL EnvPlanningTool CallingBrowser Use

Papers

WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?

ICML · 2024

ServiceNow + MILA benchmark of 33 enterprise knowledge-work tasks (forms, dashboards, service catalogs) on a real ServiceNow instance.

introduces

WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?

ICML · 2024

ServiceNow + MILA benchmark of 33 enterprise knowledge-work tasks (forms, dashboards, service catalogs) on a real ServiceNow instance.

FAQ

What is WorkArena?: Browser-based enterprise web tasks on a live ServiceNow instance - list filtering, form filling, knowledge search - covering daily knowledge-worker workflows.
What capabilities does WorkArena test?: WorkArena evaluates browser use, tool calling, planning.
How can a model improve its WorkArena score?: Tools linked to WorkArena on Sophon include BrowserGym, Openenv Browsergym RL Env (Hugging Face) - RL environments, datasets, and scaffolds that target this eval.
What license is WorkArena under?: WorkArena is available under Apache-2.0.