WebWalkerQA

📑 The paper of WebWalkerQA is available at [arXiv](https://arxiv.org/pdf/2501.07572).

📊 The dataset resource is a collection of **680** questions and answers from the WebWebWalker dataset.

🙋 The dataset is in the form of a JSON file.
The keys in the JSON include:
Question, Answer, Root_Url, and Info. The Info field contains
more detailed information, including Hop, Domain, Language,
Difficulty_Level, Source Website, and Golden_Path.
```
{
"Question": "When is the paper submission deadline for the ACL 2025 Industry Track, and what is the venue address for the conference?",
"Answer": "The paper submission deadline for the ACL 2025 Industry Track is March 21, 2025. The conference will be held in Brune-Kreisky-Platz 1.",
"Root_Url": "https://2025.aclweb.org/",
"Info":{
"Hop": "multi-source",
"Domain": "Conference",
"Language": "English",
"Difficulty_Level": "Medium",
"Source_Website": ["https://2025.aclweb.org/calls/industry_track/","https://2025.aclweb.org/venue/"],
"Golden_Path": ["root->call>student_research_workshop", "root->venue"]
}
}
```
🏋️ We also release a collection of **15k** silver dataset, which although not yet carefully human-verified, can serve as supplementary \textbf{training data} to enhance agent performance.

🙋 If you have any questions, please feel free to contact us via the [Github issue](https://github.com/Alibaba-NLP/WebWalker/issue).

⚙️ Due to the web changes quickly, the dataset may contain outdated information, such as golden path or source website. We encourage you to contribute to the dataset by submitting a pull request to the WebWalkerQA or contacting us.

💡 If you find this dataset useful, please consider citing our paper:
```bigquery
@article{wu2025webwalker,
title={Webwalker: Benchmarking llms in web traversal},
author={Wu, Jialong and Yin, Wenbiao and Jiang, Yong and Wang, Zhenglin and Xi, Zekun and Fang, Runnan and Zhang, Linhai and He, Yulan and Zhou, Deyu and Xie, Pengjun and others},
journal={arXiv preprint arXiv:2501.07572},
year={2025}
}
```

📑 WebWalkerQA 的相关研究论文可于 [arXiv](https://arxiv.org/pdf/2501.07572) 下载查阅。

📊 本数据集资源源自 WebWebWalker 数据集，包含共计680条问答对。

🙋 该数据集以JSON文件格式存储，其内置键名包括：Question（问题）、Answer（回答）、Root_Url（根网址）与Info（详细信息）。其中Info字段涵盖更为丰富的细节信息，具体包含Hop（跳转类型）、Domain（领域）、Language（语言）、Difficulty_Level（难度等级）、Source Website（来源网站）以及Golden_Path（金标路径）。

示例JSON结构如下：

{
"Question": "ACL 2025产业赛道的论文提交截止日期为何时，本次会议的举办地址是什么？",
"Answer": "ACL 2025产业赛道的论文提交截止日期为2025年3月21日，本次会议将在Brune-Kreisky-Platz 1举办。",
"Root_Url": "https://2025.aclweb.org/",
"Info":{
"Hop": "多源",
"Domain": "会议",
"Language": "英语",
"Difficulty_Level": "中等",
"Source_Website": ["https://2025.aclweb.org/calls/industry_track/","https://2025.aclweb.org/venue/"],
"Golden_Path": ["根节点->调用>学生研究研讨会", "根节点->会场"]
}
}

🏋️ 我们同时发布了包含15k条银标数据集的集合，尽管该部分数据尚未经过细致的人工核验，但可作为补充训练数据以提升AI智能体（AI Agent）的性能表现。

🙋 若您有任何疑问，欢迎通过 [Github issue](https://github.com/Alibaba-NLP/WebWalker/issue) 提交议题与我们取得联系。

⚙️ 由于网页内容更新较快，本数据集可能存在过时信息，例如金标路径或来源网站。我们诚挚邀请您通过向WebWalkerQA提交拉取请求（pull request）或直接联系我们的方式参与数据集的迭代完善。

💡 若本数据集对您的研究有所助益，请考虑引用我们的论文《WebWalker：面向网页遍历的大语言模型基准测试》，引用格式如下：
bigquery
@article{wu2025webwalker,
title={Webwalker: Benchmarking llms in web traversal},
author={Wu, Jialong and Yin, Wenbiao and Jiang, Yong and Wang, Zhenglin and Xi, Zekun and Fang, Runnan and Zhang, Linhai and He, Yulan and Zhou, Deyu and Xie, Pengjun and others},
journal={arXiv preprint arXiv:2501.07572},
year={2025}
}