diff --git a/README.md b/README.md index 74d5f72..d7ac916 100644 --- a/README.md +++ b/README.md @@ -260,7 +260,7 @@ if __name__ == "__main__": Evaluated on [AndroidWorld](https://github.com/google-research/android_world) — Google Research's gold-standard benchmark spanning 20+ real apps and 100+ complex multi-step tasks: **Artemis demonstrated exceptional robustness across the entire benchmark suite, achieving a 99%+ completion rate.**

- AndroidWorld Benchmark Comparison + AndroidWorld Benchmark Comparison

## 🚀 How ARTEMIS is Architected diff --git a/README_CN.md b/README_CN.md index 0095555..1aaf323 100644 --- a/README_CN.md +++ b/README_CN.md @@ -263,7 +263,7 @@ if __name__ == "__main__": 在 Google Research 发布的业界基准评测 [AndroidWorld](https://github.com/google-research/android_world)(涵盖 20+ 款常用应用与 100+ 项复杂多步长程任务)中:**Artemis 在全套长程任务评测中展现了高鲁棒性,取得了超过 99% 的任务完成率。**

- AndroidWorld 评测基准对比 + AndroidWorld 评测基准对比

## 🚀 ARTEMIS 是如何建构的 diff --git a/docs/assets/androidworld_benchmark_comparison.png b/docs/assets/androidworld_benchmark_comparison.png index 8d12381..08abe25 100644 Binary files a/docs/assets/androidworld_benchmark_comparison.png and b/docs/assets/androidworld_benchmark_comparison.png differ diff --git a/docs/assets/androidworld_leaderboard.png b/docs/assets/androidworld_leaderboard.png index 8d12381..08abe25 100644 Binary files a/docs/assets/androidworld_leaderboard.png and b/docs/assets/androidworld_leaderboard.png differ