WebLeaper

📦 Dataset & Task Design

WebLeaper constructs IS tasks from curated Wikipedia tables and cross-table unions:

* **Tree-Structured IS:**
* Root (question entity) $\rightarrow$ 2nd layer (key entities) $\rightarrow$ 3rd layer (attributes/linked entities)
* Each 2nd-layer node + its attributes forms a subtree; tasks require retrieving final and intermediate entities.
* **Variants**
1. **`Basic`:** Build a single-source tree from one well-formed table; dense targets in a constrained context.
2. **`Union`:** Detect maximal unions among trees that share relations (modeled as maximal biclique enumeration) to create multi-source synthesis questions.
3. **`Reverse-Union`:** Provide attribute-level clues to deduce a hidden anchor entity first, then pivot (e.g., nationality) to launch a union-style search.

> **Result:** Tasks that reward efficient exploration, resist keyword shortcuts, and stabilize metric estimation as the target count ($n$) grows.

-----

📐 Metrics: Measuring Coverage & Efficiency

* **Information-Seeking Rate (ISR):** Fraction of required entities retrieved.
$$
\mathrm{ISR} = \frac{|R\cap O|}{|R|}
$$
* **Information-Seeking Efficiency (ISE):** Target entities discovered per action step.
$$
\mathrm{ISE} = \frac{n}{T}
$$
* **Stability:** As the number of targets $n$ increases, $\mathrm{Var}(\mathrm{ISE}) = \mathcal{O}(1/n)$, yielding reliable efficiency signals during training.

-----

🔍 Method Details

1. **`Basic` (Single-Source, Dense)**

* Mine large, homogeneous Wikipedia tables.
* Root from table title; primary key columns $\rightarrow$ 2nd-layer; other columns $\rightarrow$ 3rd-layer attributes.
* Build compact, high-coverage tasks that maximize valid actions.

2. **`Union` (Multi-Source, Structured)**

* Identify maximal unions between trees sharing relation sets (e.g., `has_nationality`, `has_name`).
* Synthesize questions that require intersection/union across sources (e.g., “authors who won both Prize A and Prize B”).

3. **`Reverse-Union` (Deduction $\rightarrow$ Expansion)**

* Provide fuzzed clues at the attribute level to force anchor deduction (no direct keywords).
* Use a pivot attribute (e.g., country) from the deduced anchor to launch a new `Union`-style search over other trees.

-----

## 🚩 Citation

If this work is helpful, please kindly cite as:

```bigquery
@misc{tao2025webleaper,
title={Webleaper: Empowering efficiency and efficacy in webagent via enabling info-rich seeking},
author={Tao, Zhengwei and Shen, Haiyang and Li, Baixuan and Yin, Wenbiao and Wu, Jialong and Li, Kuan and Zhang, Zhongwang and Yin, Huifeng and Ye, Rui and Zhang, Liwen and others},
year={2025},
eprint={2510.24697},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2510.24697},
}
```

📦 数据集与任务设计

WebLeaper 基于精选的维基百科表格及跨表联合构建信息检索（Information-Seeking, IS）任务：
* **树结构信息检索任务：**
* 根节点（问题实体）→ 第二层（关键实体）→ 第三层（属性/关联实体）
* 每个第二层节点及其属性构成一棵子树；任务要求检索最终实体与中间实体。
* **任务变体**
1. **`Basic`（基础版）：** 从单个规范表格构建单源树；在受限上下文下生成稠密目标。
2. **`Union`（联合版）：** 检测共享关系的树之间的极大联合（建模为极大二部团枚举），以生成多源合成问题。
3. **`Reverse-Union`（反向联合版）：** 提供属性级线索，先推导隐藏的锚定实体，再通过枢纽（如国籍）发起联合风格的检索。

> **任务效果：** 此类任务能够激励高效探索，抵御关键词捷径，并在目标数量（$n$）增长时稳定指标估算。

-----

📐 评估指标：覆盖率与效率

* **信息检索率（Information-Seeking Rate, ISR）：** 已检索到的所需实体占总需检索实体的比例。
$$mathrm{ISR} = frac{|Rcap O|}{|R|}$$
* **信息检索效率（Information-Seeking Efficiency, ISE）：** 每操作步骤发现的目标实体数。
$$mathrm{ISE} = frac{n}{T}$$
* **稳定性：** 随着目标数量$n$增加，$mathrm{Var}(mathrm{ISE}) = mathcal{O}(1/n)$，在训练过程中可提供可靠的效率信号。

-----

🔍 方法细节

1. **`Basic`（单源稠密版）**
* 挖掘大规模同质化维基百科表格。
* 以表格标题作为根节点；主键列对应第二层节点；其余列对应第三层属性。
* 构建紧凑、高覆盖率的任务，最大化有效操作空间。

2. **`Union`（多源结构化版）**
* 识别共享关系集合（如`has_nationality`、`has_name`）的树之间的极大联合。
* 合成需要跨源交集/并集操作的问题（例如："同时获得奖项A与奖项B的作者"）。

3. **`Reverse-Union`（推导→扩展版）**
* 提供属性级模糊线索，强制进行锚定实体推导（无直接关键词）。
* 从推导得到的锚定实体中选取枢纽属性（如国家），在其他树集合上发起全新的`Union`风格检索。

-----

🚩 引用声明

若本研究对你有所帮助，请引用如下文献：
bigquery
@misc{tao2025webleaper,
title={Webleaper: Empowering efficiency and efficacy in webagent via enabling info-rich seeking},
author={Tao, Zhengwei and Shen, Haiyang and Li, Baixuan and Yin, Wenbiao and Wu, Jialong and Li, Kuan and Zhang, Zhongwang and Yin, Huifeng and Ye, Rui and Zhang, Liwen and others},
year={2025},
eprint={2510.24697},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2510.24697},
}