# RSIAgent：先广后深训练智能体应对陌生应用

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-25 22:59
- AIHOT 分数：37
- AIHOT 链接：https://aihot.news/items/cmuh3l6pd07sfrolz7d05wvl1
- 原文链接：https://x.com/rohanpaul_ai/status/2103499765371797579

## AI 摘要

RSIAgent 用课程智能体生成练习任务、执行智能体用代码解题、独立验证器校验结果，练习先覆盖相关任务再深入真实任务的难例。论文称，先广泛探索再攻难例的智能体在 4 项任务上平均得分 74.54%，直接上手难例仅 56.50%。该方法旨在替代为新应用收集数据并重训的高成本做法。

## 正文

Agents that explored widely before tackling hard cases averaged 74.54% on 4 tasks, versus 56.50% when they went straight to the hard cases, so start wide.

AI agents often fumble in unfamiliar apps. The usual fix is collecting new data and retraining, which is expensive.

In RSIAgent, a curriculum agent invents practice tasks, an actor solves them with code, and a separate verifier checks each result. Practice starts broad across related tasks, then goes deep on the real task and its hard cases.

Overall the paper says, Before putting an agent to work in a new app, let it practice broad, then deep, with a separate verifier deciding what's saved.