From cd6999bdad6ff53cebc22ff2cf753b46aa2185dc Mon Sep 17 00:00:00 2001 From: dengjiaji Date: Tue, 2 Sep 2025 21:51:44 +0800 Subject: [PATCH] fix typos --- README.md | 14 +++++++------- README_ZH.md | 14 +++++++------- 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/README.md b/README.md index 61fe55a4..c371be03 100644 --- a/README.md +++ b/README.md @@ -351,8 +351,8 @@ We tested ReMe on Appworld using qwen3-8b: | Method | pass@1 | pass@2 | pass@4 | |--------------|-----------|-----------|-----------| -| without Reme | 0.083 | 0.140 | 0.228 | -| with Reme | **0.109** | **0.175** | **0.281** | +| without ReMe | 0.083 | 0.140 | 0.228 | +| with ReMe | **0.109** | **0.175** | **0.281** | Pass@K measures the probability that at least one of the K generated samples successfully completes the task ( score=1). @@ -362,7 +362,7 @@ You can find more details on reproducing the experiment in [quickstart.md](cookb ### 🧊 Frozenlake Experiment -| Without memory | With memory | +| without ReMe | with ReMe | |:-------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------:| |

GIF 1

|

GIF 2

| @@ -370,8 +370,8 @@ We tested on 100 random frozenlake maps using qwen3-8b: | Method | pass rate | |--------------|------------------| -| without Reme | 0.66 | -| with Reme | 0.72 **(+9.1%)** | +| without ReMe | 0.66 | +| with ReMe | 0.72 **(+9.1%)** | You can find more details on reproducing the experiment in [quickstart.md](cookbook/frozenlake/quickstart.md). @@ -381,8 +381,8 @@ We tested ReMe on BFCL-V3 multi-turn-base (randomly split 50train/150val) using | Method | pass@1 | pass@2 | pass@4 | |--------------|---------------------|---------------------|---------------------| -| without Reme | 0.2472 | 0.2733 | 0.2922 | -| with Reme | 0.3061 **(+5.89%)** | 0.3500 **(+7.67%)** | 0.3888 **(+9.66%)** | +| without ReMe | 0.2472 | 0.2733 | 0.2922 | +| with ReMe | 0.3061 **(+5.89%)** | 0.3500 **(+7.67%)** | 0.3888 **(+9.66%)** | ## 📚 Resources diff --git a/README_ZH.md b/README_ZH.md index b64e09af..c7af7245 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -333,8 +333,8 @@ response = requests.post("http://localhost:8002/retrieve_task_memory", json={ | 方法 | pass@1 | pass@2 | pass@4 | |--------------|-----------|-----------|-----------| -| without Reme | 0.083 | 0.140 | 0.228 | -| with Reme | **0.109** | **0.175** | **0.281** | +| without ReMe | 0.083 | 0.140 | 0.228 | +| with ReMe | **0.109** | **0.175** | **0.281** | Pass@K 衡量的是在生成的 K 个样本中，至少有一个成功完成任务（score=1）的概率。 当前实验使用的是一个内部的 AppWorld 环境，可能存在轻微差异。 @@ -344,7 +344,7 @@ Pass@K 衡量的是在生成的 K 个样本中，至少有一个成功完成任 ### 🧊 Frozenlake 实验 -| 不使用memory | 使用memory | +| 不使用ReMe | 使用ReMe | |:-------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------:| |

GIF 1

|

GIF 2

| @@ -352,8 +352,8 @@ Pass@K 衡量的是在生成的 K 个样本中，至少有一个成功完成任 | 方法 | pass rate | |--------------|------------------| -| without Reme | 0.66 | -| with Reme | 0.72 **(+9.1%)** | +| without ReMe | 0.66 | +| with ReMe | 0.72 **(+9.1%)** | 你可以在 [quickstart.md](cookbook/frozenlake/quickstart.md) 中找到复现实验的更多细节。 @@ -363,8 +363,8 @@ Pass@K 衡量的是在生成的 K 个样本中，至少有一个成功完成任 | 方法 | pass@1 | pass@2 | pass@4 | |--------------|---------------------|---------------------|---------------------| -| without Reme | 0.2472 | 0.2733 | 0.2922 | -| with Reme | 0.3061 **(+5.89%)** | 0.3500 **(+7.67%)** | 0.3888 **(+9.66%)** | +| without ReMe | 0.2472 | 0.2733 | 0.2922 | +| with ReMe | 0.3061 **(+5.89%)** | 0.3500 **(+7.67%)** | 0.3888 **(+9.66%)** | ## 📚 相关资源