---
id: 20260916-T0-06
title: "用应用行为建模给网页智能体省token：新方法降低执行成本"
title_en: "Modeling Application Behavior Cuts Token Costs for Web Agents"
url: https://ai.daily.yangsir.net/daily/20260916-T0-06
issue_date: 2026-09-16
publish_date: 2026-09-15T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2609.13491
---

# 用应用行为建模给网页智能体省token：新方法降低执行成本

一篇新论文提出通过应用行为建模来实现token高效的任务执行，面向网页智能体。论文指出，AI智能体在各类任务中表现强劲，推动了对智能体基础设施的大规模投资，但token处理成本正在快速上升。该方法试图在网页应用自动化场景中减少不必要的token消耗。具体节省比例和测试基准需参考完整论文。对大规模部署网页智能体的团队有成本优化价值。

## English Version

**Modeling Application Behavior Cuts Token Costs for Web Agents**

A new paper proposes token-efficient task execution for web agents via application behavior modeling. It notes that strong AI agent performance across tasks has driven massive investment in agentic infrastructure, but token processing costs are rising fast. The method aims to reduce unnecessary token consumption in web application automation. Specific savings ratios and benchmarks require the full paper. It has cost-optimization value for teams deploying web agents at scale.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2609.13491)

**详情页**：https://ai.daily.yangsir.net/daily/20260916-T0-06

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*