Files
myWiki/concepts/interactive-judge.md

40 lines
1.5 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "交互式判断器Interactive Judge"
created: 2026-07-02
updated: 2026-07-02
type: concept
tags: [verification, frontend, judge, playwright, interaction]
sources:
- "[[verification-horizon-no-silver-bullet]]"
---
# 交互式判断器Interactive Judge
用于前端任务的 Agent 判断器,通过模拟真实用户交互来评估生成页面,抵抗静态判断器的长度利用。
## 三阶段 Pipeline
1. **Action Planning**单次前向传递Action Planner 从任务规范和页面信息accessibility tree、browser state、keyboard listeners一次性生成完整 action list
2. **Render Execution**Playwright server 在真实浏览器中执行 action list录制交互轨迹screenshots、DOM changes、console output
3. **Scoring**Judge model 根据 rubric checklist 评估交互轨迹 + 源码
## 关键优势
- **抵抗长度利用**:奖励来自运行时行为,而非源码长度 → 模型无法通过生成冗余 CSS/JS 骗分
- **覆盖动态行为**:多页导航、动画、状态转换、表单验证 → 静态截图无法捕获
- **效率**:单 pass 生成 action listvs 迭代 agent loop降低推理成本
## 对比静态判断器
| 特征 | Static Judge | Interactive Judge |
|------|:---:|:---:|
| 评估依据 | 源码 + 静态截图 | 运行时交互行为 |
| 长度利用 | 易被利用 | 抵抗 |
| 动态行为 | 无法覆盖 | 可覆盖 |
| 成本 | 低 | 中 |
## 参<><E58F82>
- [[verification-horizon-no-silver-bullet|论文原文]]
- [[rubric-based-evaluation|量规评估]]