# Harness Handbook：用静态分析提升智能体规划成功率

- 来源：elvis (@omarsar0)
- 发布时间：2026-07-23 22:20
- AIHOT 分数：17
- AIHOT 链接：https://aihot.virxact.com/items/cmrxlptbm001kroxp2xm8ex0z
- 原文链接：https://x.com/omarsar0/status/2080296884187652381

## AI 摘要

Harness Handbook 通过静态分析与 LLM 辅助构建三级映射，将运行时行为定位到源码位置。其 BGPD 工作流引导编码智能体从系统概览到相关函数与文件，并验证每个候选。在 Codex 和 Terminus-2 的 60 次修改请求中，规划成功率从 28.3% 提升至 38.3%、从 26.7% 提升至 45.6%，规划器 token 使用量下降 12.7% 和 8.6%。

## 正文

Great paper on self-improving agent harnesses.

（bookmark it）

If you maintain a production agent harness， finding every file behind one behavior is often harder than writing the edit.

Harness Handbook builds a three-level map from runtime behaviors to source locations using static analysis and LLM-assisted structuring.

Its BGPD workflow guides coding agents from the system overview to relevant stages， functions， and files， then verifies every candidate against current source.

Across 60 modification requests on Codex and Terminus-2， handbook guidance raised planning win rates from 28.3% to 38.3% and from 26.7% to 45.6%.

Planner token use fell 12.7% and 8.6%.

File- and symbol-level F1 improved in all 24 comparisons against GPT-5.5 and Opus 4.8 reference plans. Complete localization misses fell by as much as 25.9 points.

This is a strong pattern for coding agents that need to evolve large harnesses without losing scattered or rarely executed behavior.

Paper： https://arxiv.org/abs/2607.13285

Learn to build effective AI agents in our academy： https://academy.dair.ai/