arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.24697cs.CL
收藏

WebLeaper:通过支持富信息搜索提升WebAgent的效率与效能

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

Tongyi Lab , Alibaba Group(通义实验室,阿里巴巴集团)

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

AI总结:

针对现有LLM信息搜索智能体效率低、训练目标实体稀疏的问题,提出WebLeaper框架,将IS建模为树结构推理,用三类Wikipedia表格合成高覆盖率任务,筛选高效准确轨迹训练,在5个基准上实现效率与效能双提升。

摘要:

基于大语言模型(LLM)的智能体已成为解决开放式问题的变革性方法,而信息搜索(IS)是实现自主推理与决策的核心能力。尽管先前研究主要聚焦于提升检索深度,但我们发现当前的信息搜索智能体往往存在搜索效率低下的问题,这反过来制约了整体性能。导致这种低效的一个关键因素是训练任务中目标实体的稀疏性,这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,这是一个用于构建高覆盖率信息搜索任务并生成高效求解轨迹的框架。我们将信息搜索建模为树结构推理问题,使得数量显著更多的目标实体能够被嵌入到受限上下文中。利用经过整理的Wikipedia表格,我们提出了三种合成信息搜索任务的变体:Basic、Union和Reverse-Union,以系统性地提升信息搜索的效率与效能。最后,我们通过仅保留同时具备准确性与高效性的轨迹来整理训练轨迹,确保模型在正确性与搜索性能两方面都得到优化。我们在5个信息搜索基准(BrowserComp、GAIA、xbench-DeepSearch、WideSearch和Seal-0)的基础设置与综合设置下开展了大量实验,结果表明,与强基线模型相比,我们的方法在有效性与效率上均能持续取得提升。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑