Primary sourcearXiv cs.AI
View sourceEvent ·Single source
SOMA:用 System One 模型持续监控推理模型的思考过程
论文提出 SOMA(System One Metacognitive Awareness)框架,让 Jev 这类 System One 决策模型在 System Two 推理模型生成过程中持续监控并适时干预。SOMA 分三层:场景层用自然语言描述目标和动作,觉察层由 S1 判断行为是否出现,控制层先提醒 S2,行为持续才接管。跨任务共享一个 S1 模型和一个控制器,无需训练。在过度思考场景下,推理 token 减少最多 36% 且平均准确率仍有提升;在不可回答问题上,弃答率从 70.5% 提高到 87.2%。
Current read
让小模型当监工盯着大模型思考,超了就提醒或接管,省 36% 推理 token,弃答也更准,不用训练。
2 sources38° AI heatLast updated 2026/10/19 17:40:21
Evidence
2 sourcesRelated source 1coderabbitai
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.