# 渐进式披露在AI智能体中不具扩展性

- 来源：elvis (@omarsar0)
- 发布时间：2026-07-22 08:00
- AIHOT 分数：42
- AIHOT 链接：https://aihot.virxact.com/items/cmrvc8yvz00nvbihbmjsfc6oh
- 原文链接：https://x.com/omarsar0/status/2079718100447166533

## AI 摘要

DAIR.AI 的研究表明，智能体中的渐进式披露（agent skills 模式）效果高度依赖智能体框架。在 InfiniteBench 上测试三个框架和三个模型族发现：单本书场景下，若框架本身检索能力强则增益近乎零；多本书场景下，一层披露有效，但第二层路由层反而会破坏准确性。论文指出渐进式披露购买的是上下文而非智能。

## 正文

Progressive disclosure in agents doesn't scale.

And its benefits seems agent harness dependent.

（bookmark this one）

Finally there is a proper study on using agent skills and the effect of progressive disclosure.

Progressive disclosure is the agent skills pattern where you hand an agent a document path and let it decide what to read， from a short description down to specific passages.

Practitioners adopted it fast for book-length tasks， purely on vibes.

Researchers ran it across three agent harnesses and three model families on InfiniteBench.

On a single book：

> the gain is harness-dependent，
> large when the agent navigates raw documents poorly，
> near zero when a strong harness already retrieves on its own.

Scale to many books and raw navigation falls apart while one level of disclosure pulls ahead. A second routing level never helps and sometimes breaks accuracy.

It feels like progressive disclosure buys context， but not intelligence. It is redundant while a strong agent can find the passage itself， and decisive once the corpus is too large to read.

Paper： https://arxiv.org/abs/2607.17598

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