斯坦福与Together AI论文：混合Agent推理提速62%且精度更高
New Stanford and Together AI paper finds that cheaper reasoning need not cost ac…
这篇论文揭示了“静默推理”的新范式，用极小代价换取显著性能提升，做Agent开发的同学值得参考其架构设计思路。
New Stanford and Together AI paper finds that cheaper reasoning need not cost accuracy, as hybrid agents cut decoding compute by 62.5% to 72.9% and still scored higher.
斯坦福大学与Together AI联合发表的新论文发现，更廉价的推理无需牺牲准确性，混合智能体将解码计算量削减了62.5%至72.9%，且得分更高。
Shows that agents run faster and score higher when most thinking happens in hidden vectors, not written text.
研究表明，当大部分思考过程发生在隐藏向量中而非文本中时，智能体的运行速度更快，得分也更高。
Today's agents write every reasoning step as text tokens, which is slow and costly. Models that reason in their internal vectors are faster, but they cannot call tools and humans cannot read what they think.
当前的智能体将每个推理步骤都作为文本token写入，这既缓慢又昂贵。在内部向量中进行推理的模型速度更快，但它们无法调用工具，人类也无法读取其思考内容。
HybridAgent adds a small adapter that feeds the model's internal state back as its next input, so it can think without writing words. It switches to text for tool calls and key decisions, and its silent steps can still be decoded into readable words.
HybridAgent添加了一个小型适配器，将模型的内部状态反馈为其下一个输入，使其能够在不书写文字的情况下进行思考。它在调用工具和做出关键决策时切换为文本模式，而其静默步骤仍可被解码为可读文字。
On GAIA, the 14B version scored 52.4, above 43.7 for the same model trained as a text-only agent with ARPO. It also ran 2.1× faster than matched text agents.
在GAIA基准测试中，14B版本的得分为52.4，高于使用ARPO训练的同款纯文本智能体的43.7分。其运行速度也比匹配条件的文本智能体快2.1倍。
If your agent spends tokens on routine reasoning, try keeping that reasoning internal and saving text for tool calls and steps humans must check.
如果你的智能体在常规推理上消耗了大量token，建议将这些推理保留在内部，仅将文本用于工具调用和人类必须检查的步骤。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力