WebClipper: 基于图的轨迹修剪高效进化网络代理
WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning
AI总结：
本文提出WebClipper框架，通过图基修剪压缩网络代理轨迹，减少20%的工具调用次数并提升准确性，引入F-AE Score指标平衡精度与效率。
摘要：
基于网络代理的深度研究系统在解决复杂信息检索任务中展现出强大潜力，但其搜索效率仍待探索。我们观察到许多最先进的开源网络代理依赖长工具调用轨迹，包含循环推理和无效分支探索。为此，我们提出WebClipper框架，通过图基修剪压缩网络代理轨迹。具体而言，我们将代理的搜索过程建模为状态图，并将轨迹优化转化为最小必要有向无环图（DAG）挖掘问题，生成保留关键推理并消除冗余步骤的修剪轨迹。继续在这些优化轨迹上训练，使代理向更高效的搜索模式进化，并减少约20%的工具调用次数同时提升准确性。此外，我们引入了一个新的指标F-AE Score，用于衡量模型在平衡精度和效率方面的整体性能。实验表明，WebClipper在优异性能下压缩工具调用次数，为网络代理设计中平衡有效性和效率提供了实用见解。
英文摘要：
Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning. Concretely, we model the agent's search process as a state graph and cast trajectory optimization as a minimum-necessary Directed Acyclic Graph (DAG) mining problem, yielding pruned trajectories that preserve essential reasoning while eliminating redundant steps. Continued training on these refined trajectories enables the agent to evolve toward more efficient search patterns and reduces tool-call rounds by about 20% while improving accuracy. Furthermore, we introduce a new metric called F-AE Score to measure the model's overall performance in balancing accuracy and efficiency. Experiments demonstrate that WebClipper compresses tool-call rounds under excellent performance, providing practical insight into balancing effectiveness and efficiency in web agent design.
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。
