WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909874032476160 |
|---|---|
| author | Tao, Zhengwei Shen, Haiyang Li, Baixuan Yin, Wenbiao Wu, Jialong Li, Kuan Zhang, Zhongwang Yin, Huifeng Ye, Rui Zhang, Liwen Wang, Xinyu Xie, Pengjun Zhou, Jingren Jiang, Yong |
| author_facet | Tao, Zhengwei Shen, Haiyang Li, Baixuan Yin, Wenbiao Wu, Jialong Li, Kuan Zhang, Zhongwang Yin, Huifeng Ye, Rui Zhang, Liwen Wang, Xinyu Xie, Pengjun Zhou, Jingren Jiang, Yong |
| contents | Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior research has largely focused on improving retrieval depth, we observe that current IS agents often suffer from low search efficiency, which in turn constrains overall performance. A key factor underlying this inefficiency is the sparsity of target entities in training tasks, which limits opportunities for agents to learn and generalize efficient search behaviors. To address these challenges, we propose WebLeaper, a framework for constructing high-coverage IS tasks and generating efficient solution trajectories. We formulate IS as a tree-structured reasoning problem, enabling a substantially larger set of target entities to be embedded within a constrained context. Leveraging curated Wikipedia tables, we propose three variants for synthesizing IS tasks, Basic, Union, and Reverse-Union, to systematically increase both IS efficiency and efficacy. Finally, we curate training trajectories by retaining only those that are simultaneously accurate and efficient, ensuring that the model is optimized for both correctness and search performance. Extensive experiments on both basic and comprehensive settings, conducted on five IS benchmarks, BrowserComp, GAIA, xbench-DeepSearch, WideSearch, and Seal-0, demonstrate that our method consistently achieves improvements in both effectiveness and efficiency over strong baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking Tao, Zhengwei Shen, Haiyang Li, Baixuan Yin, Wenbiao Wu, Jialong Li, Kuan Zhang, Zhongwang Yin, Huifeng Ye, Rui Zhang, Liwen Wang, Xinyu Xie, Pengjun Zhou, Jingren Jiang, Yong Computation and Language Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior research has largely focused on improving retrieval depth, we observe that current IS agents often suffer from low search efficiency, which in turn constrains overall performance. A key factor underlying this inefficiency is the sparsity of target entities in training tasks, which limits opportunities for agents to learn and generalize efficient search behaviors. To address these challenges, we propose WebLeaper, a framework for constructing high-coverage IS tasks and generating efficient solution trajectories. We formulate IS as a tree-structured reasoning problem, enabling a substantially larger set of target entities to be embedded within a constrained context. Leveraging curated Wikipedia tables, we propose three variants for synthesizing IS tasks, Basic, Union, and Reverse-Union, to systematically increase both IS efficiency and efficacy. Finally, we curate training trajectories by retaining only those that are simultaneously accurate and efficient, ensuring that the model is optimized for both correctness and search performance. Extensive experiments on both basic and comprehensive settings, conducted on five IS benchmarks, BrowserComp, GAIA, xbench-DeepSearch, WideSearch, and Seal-0, demonstrate that our method consistently achieves improvements in both effectiveness and efficiency over strong baselines. |
| title | WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.24697 |