WebLeaper：通过赋能信息密集型寻径提升网络智能体的效能与效率

WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking

October 28, 2025

作者: Zhengwei Tao, Haiyang Shen, Baixuan Li, Wenbiao Yin, Jialong Wu, Kuan Li, Zhongwang Zhang, Huifeng Yin, Rui Ye, Liwen Zhang, Xinyu Wang, Pengjun Xie, Jingren Zhou, Yong Jiang

cs.AI

摘要

基于大语言模型（LLM）的智能体已成为解决开放性问题的重要突破，其中信息检索（IS）作为实现自主推理与决策的核心能力尤为关键。尽管现有研究主要聚焦于提升检索深度，我们发现当前IS智能体普遍存在搜索效率低下的问题，进而制约整体性能。这种低效现象的核心成因在于训练任务中目标实体的稀疏性，限制了智能体学习并泛化高效搜索行为的机会。为应对这些挑战，我们提出WebLeaper框架——通过构建高覆盖度的IS任务并生成高效解决路径来优化性能。我们将IS问题形式化为树状推理结构，使得在有限上下文中能嵌入更大量的目标实体。借助精选的维基百科表格，我们设计了基础型、联合型及反向联合型三种任务生成变体，系统化提升IS的效能与效率。最后通过筛选兼具准确性与高效性的训练轨迹，确保模型在正确性与搜索性能上同步优化。在BrowserComp、GAIA、xbench-DeepSearch、WideSearch和Seal-0五个IS基准测试集上进行的广泛实验表明，无论是基础场景还是复杂场景，我们的方法均能持续超越强基线模型，在效果与效率上实现双重提升。

English

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.