这篇论文用三个Harness和三个模型测了渐进式披露，发现小规模下效果看脸，大规模下才有用，二级路由反而坏事，值得搞智能体的人看看。
该研究在InfiniteBench上使用三种Agent Harness和三种模型家族（如Llama、Mistral等）测试了渐进式披露模式。对于单本书任务，增益依赖Harness：当智能体导航原始文档能力差时增益大，强Harness自带检索时增益接近零。扩展到多本书时，原始导航失败，一级披露效果领先，但二级路由层从未帮助且有时降低精度。论文表明渐进式披露主要提供上下文而非智能，在大规模语料下才体现关键作用。
Progressive disclosure in agents doesn't scale. And its benefits seems agent harness dependent. (b...
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: arxiv.org/abs/2607.17598 Learn to build effective AI agents in our academy: academy.dair.ai 💬 2 🔄 0 ❤️ 6 👀 980 📊 3 ⚡