利用合成监督技术适配网络智能体

摘要

网络智能体因缺乏针对特定环境任务及示范数据而难以适应新网站。近期研究尝试通过合成数据生成应对这一挑战，但这些方法存在数据质量问题：合成任务包含无法执行的幻觉内容，且采集的行为轨迹存在冗余或错位动作的噪声。本文提出SynthAgent——一个通过任务与轨迹双重优化来提升合成数据质量的完全合成监督框架。我们的方法首先通过对网页元素进行分类型探索来合成多样化任务，确保对目标环境的高效覆盖。在轨迹采集过程中，当检测到任务与实际观察存在冲突时，我们会对任务进行优化，在保持任务一致性的同时减少幻觉。采集完成后，我们基于全局上下文对轨迹进行优化以消除潜在噪声或错位。最终，我们利用优化后的合成数据对开源网络智能体进行微调，使其适应目标环境。实验结果表明，SynthAgent在性能上超越现有合成数据方法，验证了高质量合成监督的重要性。代码将公开于https://github.com/aiming-lab/SynthAgent。

English

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues where synthesized tasks contain hallucinations that cannot be executed, and collected trajectories are noisy with redundant or misaligned actions. In this paper, we propose SynthAgent, a fully synthetic supervision framework that aims at improving synthetic data quality via dual refinement of both tasks and trajectories. Our approach begins by synthesizing diverse tasks through categorized exploration of web elements, ensuring efficient coverage of the target environment. During trajectory collection, we refine tasks when conflicts with actual observations are detected, mitigating hallucinations while maintaining task consistency. After collection, we conduct trajectory refinement with a global context to mitigate potential noise or misalignments. Finally, we fine-tune open-source web agents on the refined synthetic data to adapt them to the target environment. Experimental results demonstrate that SynthAgent outperforms existing synthetic data methods, validating the importance of high-quality synthetic supervision. The code will be publicly available at https://github.com/aiming-lab/SynthAgent.

利用合成监督技术适配网络智能体

Adapting Web Agents with Synthetic Supervision

摘要

Support