让AI网页代理越用越高效，通过实时提炼技能减少计算开销。
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
- 在线提炼技能，构建结构化技能库，动态优化决策路径。
- 在910项任务中成功率达58.3%，比基线少用58%以上token。
- 适合关注推理效率与长期运行成本的智能体研发者。
近期多模态网页代理依赖增加推理时计算，包括回溯搜索、验证器调用、离线技能发现和专用模型堆叠。这引发核心问题：代理能否在积累经验后变得更高效，而非更昂贵？我们分析VisualWebArena轨迹，发现三类低效来源：重复动作循环、隐藏发现成本、提示缓存复用率低。提出PANDO，一种单轮次在线技能蒸馏框架，维护结构化技能库，融合进度反思、置信度驱动技能降级、层级路由、视觉压缩与缓存感知提示。在910个VisualWebArena任务上，PANDO成功率达58.3%，优于SGV（54.0%）和我们的WALT复现（45.2%），同时比SGV少用58% token，比WALT少用61% token，且无需预评估发现预算。300任务消融实验表明，规则与流程带来主要成功率提升；路由、压缩与缓存感知提示将更大技能库转化为更低边际token成本。最后引入三项轨迹级效率指标——动作重复率、步骤开销比、提示缓存利用率——使效率超越最终成功率而可见。
原文摘要 · Abstract (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.
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。