Files
myWiki/concepts/capability-control-tradeoff.md
2026-06-01 10:46:01 +08:00

36 lines
1.3 KiB
Markdown
Raw 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: "Capability-Control Tradeoff能力-控制权衡)"
created: 2026-05-23
updated: 2026-05-23
type: concept
tags: [agent, tradeoff, security, capability, control]
sources: [raw/papers/agent-harness-engineering-survey-2026.md]
confidence: high
---
# Capability-Control Tradeoff
> 更强的 Harness 给 Agent 更多权力,但每次能力扩展都增大控制问题。这不是安全附加组件,而是连接工具 Schema、上下文策略、运行时权限、身份、审计和人机审批的设计轴。
## 权衡的具象化
| 能力扩展 | 控制成本 |
|---------|---------|
| 更大的工具菜单 | 选择错误增加、prompt injection 表面扩大 |
| 持久记忆 | 来源追踪provenance、陈旧性、隐私风险 |
| 宽松沙箱 | 自主执行有用但爆炸半径扩大 |
| 自主权限 | 需要更细粒度的身份、审计和恢复机制 |
## 设计含义
- 不是"先建功能再加固"的附加模型
- 工具 Schema、上下文策略、运行时权限、身份、审计、人工审批**从设计之初就应统一考虑**
- 每增加一项能力都需要同步增强控制边界
## 相关概念
- [[cost-quality-speed-trilemma]]
- [[governance-security]] — G 层是 control 侧的体现
- [[binding-constraint-thesis]]
- [[agent-harness-engineering-survey]]