跳到正文
𝕏 Rohan Paul(x.com)·· 2 天前品質評分57
重點導讀

AI 助理做機器學習研究時,常只反覆修改程式、比較分數,遇到難題可能一直修補方向錯誤的方案。

  • Pro2 Agent 會先記下它認為卡住進度的原因、可能的解法和信心,再一次只改一個地方做實驗,根據結果更新判斷。文中提到,它在 75 項 MLE-Bench 任務上用 48 小時達到 76.0% 獎牌率。
  • 在 MLE-Bench Lite 上,第一個方案的獎牌率為 57.6%,MARS 則為 28.8%。這提供了一種設計研究型 AI 助理的方法:先找出瓶頸,再用小實驗檢查。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·2 天前
𝕏

New Google and Johns Hopkins paper shows that AI research agents do better when they track what limits performance, not just which code scored best.

Agents that do ML research usually loop on code: change it, score it, keep the best. On hard tasks they can get stuck tweaking a solution that is wrong at its core.

Pro2 Agent first builds a "Problem State": the bottlenecks it suspects, candidate fixes from the literature, and how confident it is in each. It then runs single-variable experiments that update those beliefs before committing changes.

On all 75 MLE-Bench tasks, it reached a 76.0% medal rate with 48 hours, the highest reported, using Gemini 3.5 Flash for coding. On MLE-Bench Lite, its first solution already medaled on 57.6% of tasks, against 28.8% for MARS.

If you build research agents, make them write down and update what is blocking progress, and test 1 change per experiment.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論