Project report / GitHub evidence

BrowserGym Model Card

这是可索引项目报告证据页:它保留 BrowserGym Model Card 的源材料入口、机制线索和限制提醒;正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。

BrowserGym Model Card

FieldValue
RepositoryServiceNow/BrowserGym
CategoryWeb Agent Benchmark Gym
Stars / forks snapshot1200 / 174
LanguagePython
LicenseMIT
Raw captureraw-github/servicenow_browsergym.md
Updated byhourly public metadata update, 2026-05-24

1. Role in Self Evolve

ServiceNow BrowserGym 是网页任务自动化的 Gym 环境,整合 MiniWoB、WebArena、VisualWebArena、WorkArena、AssistantBench、WebLINX、OpenApps、TimeWarp 等 web agent benchmark。

2. Working Principle

Gym environment -> browser task benchmarks -> agent loop -> reward/termination metrics

3. Evidence Path

web GitHub page observed README, 385 commits, 1.2k stars, 174 forks, browsergym package install instructions, benchmark list, and AgentLab integration; shell GitHub API was blocked by DNS and gh auth was invalid, so this run marks freshness as web-page observed rather than API verified.

4. Teaching Use

Use this card to explain whether a repository is a runtime, benchmark, harness-evolution loop, memory/skill substrate, or resource index. The key reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.

5. Limits

当前未克隆源码,未运行 benchmark 或 SDK examples;star/fork/commit 快照来自公开 GitHub 页面文本或可见页面片段。