Jeva：从第一性原理出发的系统一模型

Jeva: System One Models from First Principles

October 13, 2026

作者: Qi Li, Xinchao Wang

cs.AI

摘要

系统 1 模型能够实现直接、低延迟的决策。然而，近期从序列化文本预测答案的做法本身并未尊重决策问题的结构。我们认为，当前设计对四项重要的结构要求重视不足。（i）空值感知：模型应区分答案缺失与候选之间的不确定性；（ii）排列不变：重新排列备选项不应改变决策；（iii）选项可扩展：候选集增大不应要求重新定义输出空间；（iv）可缓存：对反复出现的备选项进行的与请求无关的计算应可跨请求复用。我们提出 Jeva，一种决策原生架构，能够联合满足这些要求。共享编码器分别表示请求与每个选项，而紧凑的决策栈仅基于不可变的选项记忆来细化请求状态。对称聚合产生置换等变概率；共享评分可适应可变大小的候选集。一个独立的覆盖度估计区分答案缺失与候选竞争，从而支持显式的空结果。与请求无关的选项表示和层投影支持在新组装的集合之间复用。这些机制将 Choice、Noul 和 Score 三类输出统一起来。在各项评估中，Jeva 将强大的类型化决策性能与近乎完美的空值检测相结合，并且在任何测试过的排列下都没有决策翻转。它可扩展至数千个候选，并通过跨请求复用显著降低延迟，同时不改变决策。

English

System one models enable direct, low-latency decision-making. Yet recent practice of predicting an answer from serialized text does not, by itself, respect the structure of a decision problem. We argue that current designs underemphasize four important structural requirements. (i) null-aware: Models should distinguish answer absence from uncertainty among candidates; (ii) permutation-invariant: Reordering alternatives should not change the decision; (iii) option-scalable: Growing candidate sets should not require redefining the output space; (iv) cacheable: Request-independent computation over recurring alternatives should be reusable across requests. We introduce Jeva, a decision-native architecture that addresses these requirements jointly. A shared encoder independently represents the request and each option, while a compact decision stack refines only the request state against immutable option memory. Symmetric aggregation yields permutation-equivariant probabilities; shared scoring accommodates variable-size candidate sets. A separate coverage estimate distinguishes answer absence from candidate competition, enabling explicit null outcomes. Request-independent option representations and layer projections support reuse across newly assembled sets. These mechanisms unify Choice, Noul, and Score outputs. Across evaluations, Jeva combines strong typed-decision performance with near-perfect null detection and no decision flips under any tested permutations. It scales to thousands of candidates and substantially reduces latency through cross-request reuse without changing decisions.