AI 不再逐字生成答案，直接给你概率
大模型回答问题时，默认是逐字“想”出来的——这带来准确率，也带来慢、贵、答案不稳定。Drex 换了个思路：它不生成文字，而是直接在你给的几个选项上输出一个概率分布，比如“选 A 的概率 0.7，选 B 0.3”。这就像把“写作文”变成“做选择题”，速度从秒级降到 183 毫秒，而且把选项顺序打乱，答案也不会变。它靠强化学习调优，在公开评测上追平了 GPT-6 Sol，落后 Claude Opus 5.5 仅 1.6 分。这不是你明天能用的产品，但它指向一个趋势：AI 正在从“会说话”转向“会做决定”，而做决定，本来就不需要说那么多话。
📄 原文摘要(英文)
Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide range of tasks. In production, however, they give inconsistent answers, require parsing of outputs, and add cost and latency. Decision models address this: given a question and a set of options supplied by the user, they return a probability distribution over the options without autoregressive decoding. We present Drex, a family of four open decision models with 8B (DLM), 9B (v1.5), 35B with 3B active (v2.0), and 27B (Max) parameters. Each request consists of a state (a document, record, or agent context, optionally with images) and questions about it, each asking for a choice among options, a yes/no judgment, or a score on an ordered scale. Training combines supervised fine-tuning with reinforcement learning from adjusted feedback (RLAF), plus vision tuning for Max. Ablations show that RLAF improves accuracy and that consistency losses improve robustness to option order. On Decision Index 0.4.1, Max sets a new state of the art among the decision models we compare (67.52 on the public suite vs. 60.70 for Jev 1.14.0). On Decision Bench v4, it is statistically tied with d3-turbo and GPT-6 Sol and trails Claude Opus 5.5 by 1.6 points, and it has the highest accuracy among decision models on DecideBench. Max answers a typical request in 183 ms, against about 2.0 s for GPT-6 Sol and 3.5 s for Claude Opus 5.5, and its outputs are stable under option reordering. All four models are open source: https://github.com/nace-ai/drex-decision-models