Tag
该论文研究在智能体循环中，System One 模型选择错误动作的原因，发现大多数错误动作是在正确读取状态事实后仍行动错误，而非误解输入，并揭示模型无法组合已知事实来确定下一步动作。
作者重新评估Jev类模型的价值，认为随着模型足够快和便宜，原本靠if-else拼接的业务逻辑、实时语音交互、计算机操作和机器人决策都可以交给System 1模型处理，形成SOTA后台深思考模型与System 1实时模型分工的新范式。
This paper presents a paired, self-audited evaluation of two System-1 decision models (open-weight Laya and hosted Jev) across 11 agent-harness decision points, finding Jev significantly more accurate on 9 of 11 tasks while auditing several analysis errors that had distorted prior deployment claims.