20260706:新增一些文章
This commit is contained in:
38
concepts/agentic-quality-judge.md
Normal file
38
concepts/agentic-quality-judge.md
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
title: "Agent 质量判断器(Agentic Quality Judge)"
|
||||
created: 2026-07-02
|
||||
updated: 2026-07-02
|
||||
type: concept
|
||||
tags: [verification, quality-filtering, swe-bench, judge]
|
||||
sources:
|
||||
- "[[verification-horizon-no-silver-bullet]]"
|
||||
---
|
||||
|
||||
# Agent 质量判断器(Agentic Quality Judge)
|
||||
|
||||
自动评估 SWE 类任务质量(instruction 的清晰度和 test-instruction 的对齐度)的 Agent 判断器,作为 [[test-driven-rewards|测试驱动奖励]] 的语义过滤器。
|
||||
|
||||
## 工作原理
|
||||
|
||||
基于 MiniSWEAgent 框架,判断器主动探索 Docker 化的仓库环境:
|
||||
1. 检查 instruction 和环境是否足够自包含(`instruct_clear`)
|
||||
2. 验证 test suite 是否与所述任务匹配(`instruct_ut_align`)
|
||||
3. 综合判定 `overall_good`
|
||||
|
||||
## 设计选择
|
||||
|
||||
- **Base judge model**:Qwen-Plus / Qwen-Max
|
||||
- **投票机制**:3-voting / 5-voting majority voting
|
||||
- **辅助信息**:few-shot demonstrations(提升 instruct_ut_align 精度)、ground-truth patch(提升 recall)
|
||||
|
||||
## 效果
|
||||
|
||||
- 在 human-annotated benchmark 上 F1 = 76-81%
|
||||
- 质量过滤后的数据使 RL 在 SWE-bench Multilingual 和 Pro 上显著提升
|
||||
- 低 solve-rate 任务中低质量实例占比高 → 质量过滤提升采样效率和奖励可靠性
|
||||
|
||||
## 参考
|
||||
|
||||
- [[verification-horizon-no-silver-bullet|论文原文]]
|
||||
- [[test-driven-rewards|测试驱动奖励]]
|
||||
- [[behavior-monitoring-rl|行为监控RL]]
|
||||
Reference in New Issue
Block a user