HybridAgent：推理藏进内部向量，解码算力省 62.5% 还更准
斯坦福和 Together AI 让智能体把思考藏进向量，解码算力省 62.5%，GAIA 反而更准。
Stanford 与 Together AI 的论文提出 HybridAgent，用一个小适配器把模型内部状态回喂为下一步输入，让多数推理在隐藏向量中完成而不写成文字。智能体只在调用工具和关键决策时切换回文本，静默步骤仍可解码成可读文字供人检查，解码计算量因此降低 62.5% 至 72.9%。在 GAIA 基准上，14B 版本得 52.4 分，高于同模型用 ARPO 训练的纯文本智能体的 43.7 分，速度快 2.1 倍。
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. Shows that agents run faster and score higher when most thinking happens in hidden vectors, not written text.
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.
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.
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.
If your agent spends tokens on routine reasoning, try keeping that reasoning internal and saving text for tool calls and steps humans must check.