无需人工标注，自动在网页中探索生成训练数据，提升浏览器代理性能。
NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
- 通过反向标注探索轨迹中的动作序列，自动生成训练示范。
- 在WebArena和WebVoyager上分别达到16%和35%成功率，超越零样本LLaMA-3.1-8b。
- 适合无监督训练浏览器智能体的研究者与开发者使用。
我们提出NNetNav，一种在真实网络环境中无需人工监督的网页交互方法，可生成合成示范用于训练浏览器代理。给定任意网站，NNetNav通过回溯探索策略的动作序列进行反向标注，构建示范数据。现有训练方法严重依赖昂贵的人工标注，而此前基于交互的方法难以有效搜索指数级增长的探索空间。相比之下，NNetNav利用语言指令的层次结构：复杂任务通常可分解为简单子任务，从而在中间轨迹无法标注有意义子任务时自动剪枝交互过程。用10,000条由NNetNav自动生成的示范微调后的 exttt{LLama-3.1-8b}在WebArena上取得超过16%的成功率，在WebVoyager上达35%，分别较零样本 exttt{LLama-3.1-8b}提升15个百分点和31个百分点，优于零样本GPT-4，成为当前无监督方法中的最佳表现。
原文摘要 · Abstract (English)
We introduce NNetNav, a method for unsupervised interaction with websites that generates synthetic demonstrations for training browser agents. Given any website, NNetNav produces these demonstrations by retroactively labeling action sequences from an exploration policy. Most work on training browser agents has relied on expensive human supervision, and the limited prior work on such interaction-based techniques has failed to provide effective search through the exponentially large space of exploration. In contrast, NNetNav exploits the hierarchical structure of language instructions to make this search more tractable: Complex instructions are typically decomposable into simpler sub-tasks, allowing NNetNav to automatically prune interaction episodes when an intermediate trajectory cannot be annotated with a meaningful sub-task. \texttt{LLama-3.1-8b} finetuned on 10k NNetNav self-generated demonstrations obtains over 16\% success rate on WebArena, and 35\% on WebVoyager, an improvement of 15pts and 31pts respectively over zero-shot \texttt{LLama-3.1-8b}, outperforming zero-shot GPT-4 and reaching the state-of-the-art among unsupervised methods, for both benchmarks.
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。