通过图剪枝压缩网页代理搜索轨迹，提升效率与准确率
WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning
- 将搜索过程建模为状态图，挖掘最小必要有向无环图以剪枝冗余步骤
- 在保持高精度前提下减少约20%的工具调用轮次
- 提出F-AE Score衡量准确性与效率平衡，适合优化智能搜索系统
基于网页代理的深度研究系统在解决复杂信息检索任务方面展现出巨大潜力，但其搜索效率尚未得到充分探索。我们观察到，许多先进的开源网页代理依赖于包含循环推理和无效分支探索的长工具调用轨迹。为此，我们提出WebClipper框架，通过基于图的剪枝压缩代理轨迹。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，从而生成保留核心推理且去除冗余步骤的剪枝轨迹。在这些优化轨迹上持续训练可使代理演化出更高效的搜索模式，在工具调用轮次减少约20%的同时提升准确率。此外，我们引入新指标F-AE Score以衡量模型在准确率与效率之间的综合表现。实验表明，WebClipper在保持优异性能的前提下显著压缩了工具调用轮次，为网页代理设计中的有效性与效率平衡提供了实用洞见。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。