PANDO：通过在线技能蒸馏实现高效的多模态AI智能体

摘要

多模态网页智能体的近期进展通常依赖推理时计算量的增加，包括展开式搜索、验证器传递、离线技能发现以及专家模型堆叠。这引出一个核心问题：网页智能体能否在积累经验的过程中变得更高效，而非更昂贵？我们首先分析了VisualWebArena中的轨迹数据，识别出三个反复出现的低效来源：重复动作循环、隐藏的发现成本以及低提示缓存复用率。随后我们提出PANDO——一种单次展开的在线技能蒸馏框架，该框架维护结构化的技能库，并融合进度反思、基于置信度的技能降级、分层路由、视觉压缩以及缓存感知提示。在全部910个VisualWebArena任务上，PANDO实现了58.3%的成功率，优于SGV（54.0%）和我们复现的WALT（45.2%），同时相比SGV减少58%的令牌使用量，相比WALT减少61%，且无需任何预评估发现预算。进一步的300任务消融实验表明，规则与惯例贡献了大部分成功率提升，而路由、压缩和缓存感知提示则将更大的技能库转化为更低的边际令牌成本。最后，我们引入三项轨迹级效率指标——动作重复率、步骤开销比和提示缓存利用率，使效率在最终成功率之外变得可见。

English

Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question: can a web agent become more efficient as it accumulates experience, rather than more expensive? We first analyze trajectories from VisualWebArena and identify three recurring sources of inefficiency: repeat-action loops, hidden discovery costs, and low prompt-cache reuse. We then introduce PANDO, a single-rollout online skill-distillation framework that maintains a structured Skill Library and combines progress reflection, confidence-based skill demotion, hierarchical routing, visual compression, and cache-aware prompting. On the full set of 910 VisualWebArena tasks, PANDO achieves a 58.3% success rate, outperforming SGV (54.0%) and our WALT reproduction (45.2%), while using 58% fewer tokens than SGV and 61% fewer tokens than WALT, without any pre-evaluation discovery budget. A 300-task ablation further shows that rules and routines provide most of the success gains, while routing, compression, and cache-aware prompting convert the larger skill library into lower marginal token cost. Finally, we introduce three trajectory-level efficiency metrics -- Action Repetition Rate, Step Overhead Ratio, and Prompt Cache Utilization -- to make efficiency visible beyond terminal success.