为网页智能体添加可回滚机制，提升复杂网页环境下的导航鲁棒性。
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
- 引入显式回滚机制，允许智能体返回历史导航状态。
- 在两个真实网页导航基准上表现优于贪心策略，零样本与微调均有效。
- 适合需要高可靠性网页操作的场景，如自动化测试或数据采集。
随着大语言模型的发展，网页智能体能力显著提升。然而，在复杂动态的网络环境中，仍需更强的规划与搜索能力。以往研究多采用贪心的一维搜索策略，难以从错误状态中恢复。本文提出一种显式回滚机制，使智能体能够基于其导航轨迹回退到先前状态，从而直接控制搜索过程，实现更高效、可靠的网页导航。我们在两个真实网页导航基准上进行了零样本和微调设置下的实验，结果表明该方法有效提升了智能体的表现。
原文摘要 · Abstract (English)
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning and search abilities. Previous studies usually adopt a greedy one-way search strategy, which may struggle to recover from erroneous states. In this work, we enhance web agents with an explicit rollback mechanism, enabling the agent to revert back to a previous state in its navigation trajectory. This mechanism gives models the flexibility to directly control the search process, leading to an effective and efficient web navigation method. We conduct experiments on two live web navigation benchmarks with zero-shot and fine-tuning settings. The results demonstrate the effectiveness of our proposed approach.
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。