用大模型模拟人工标注流程，让小模型学会上网操作。
Structured Distillation of Web Agent Capabilities Enables Generalization
- 用多个小模型分工生成网页操作轨迹，模仿人类标注流程。
- 训练出的90亿参数模型在WebArena上达41.5分，超主流闭源模型。
- 可在未见过的企业平台保持性能，适合本地部署的智能助手。
前沿大模型虽能复杂网页导航，但成本高且依赖外部接口，难以本地部署。本文提出Agent-as-Annotators框架，通过类比人类标注角色，将任务设计、标注与监督拆分为模块化大模型组件。以Gemini 3 Pro为教师，生成6个网页环境中的3000条轨迹，经质量过滤后保留2322条，用于纯监督微调90亿参数学生模型。该模型在WebArena上取得41.5%得分，超越Claude 3.5 Sonnet（36.0%）和GPT-4o（31.5%），接近两倍于此前开源最佳结果（Go-Browse，21.7%）。在未见环境WorkArena L1上提升18.2个百分点，并在三个额外基准上持续领先。消融实验表明，判别过滤、评估提示和推理轨迹均带来可衡量提升。结果证明，仅需单一前沿教师即可生成足够高质量轨迹，训练出可本地部署的高性能网页代理。
原文摘要 · Abstract (English)
Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. Using Gemini 3 Pro as teacher, we generate 3,000 trajectories across six web environments and fine-tune a 9B-parameter student with pure supervised learning on the 2,322 that pass quality filtering. The resulting model achieves 41.5% on WebArena, surpassing closed-source models such as Claude 3.5 Sonnet (36.0%) and GPT-4o (31.5%) under the same evaluation protocol, and nearly doubling the previous best open-weight result (Go-Browse, 21.7%). Capabilities transfer to unseen environments, with an 18.2 percentage point gain on WorkArena L1 (an enterprise platform never seen during training) and consistent improvements across three additional benchmarks. Ablations confirm that each pipeline component contributes meaningfully, with Judge filtering, evaluation hints, and reasoning traces each accounting for measurable gains. These results demonstrate that structured trajectory synthesis from a single frontier teacher is sufficient to produce competitive, locally deployable web agents. Project page: https://agent-as-annotators.github.io
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。