跳到正文
𝕏 elvis(x.com)·· 16 天前品質評分43
重點導讀

summary_zh: Nace AI 釋出 Drex 系列決策模型,27B 版在 Decision Bench v4 與 Claude Opus 5.5 只差 1.6 分,回應時間 183 ms。

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:

elvis
elvis@omarsar0
·16 天前
𝕏

Banger report on foundation decision models.

This work presents a 27B open decision model that lands within 1.6 points of Claude Opus 5.5 on Decision Bench v4 and answers in 183 ms instead of 3.5s.

Nace AI released Drex, a family of four open decision models at 8B, 9B, 35B with 3B active, and 27B.

You give the model a state, such as a document, a record, or an agent's context, plus questions with a fixed set of options. It returns a probability for each option without generating text.

The 27B Max model scores 67.52 on the public Decision Index 0.4.1 suite, against 60.70 for Jev 1.14.0.

On Decision Bench v4, it is statistically tied with GPT-6 Sol and d3-turbo. It also has the best accuracy among decision models on DecideBench.

Model Training:

After fine-tuning, training adds reinforcement learning from adjusted feedback (RLAF). A teacher model proposes a probability for each option, and the verified answer adjusts it, so the model trains on calibrated targets in place of one-hot labels. RLAF adds 2.0 Decision Index points, and a consistency loss lowers the rate of flipped answers when the options are reordered from 6.3% to 4.2%.

HF: https://t.co/uk9ZrkBPaQ

Paper: https://t.co/KO0rLPpG7k

Chat with Paper: https://t.co/AXgvBk20Cd

推文來源 · X (Twitter)在 X 參與討論
來源: elvis (x.com)
在 X 查看推文

讀者討論

理性交流 · 即時討論