SOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One Models
Reasoning models often run into problems without noticing them, even when symptoms are visible in their own text. In humans, metacognition separates monitoring from control: fast, intuitive signals keep watch while slow, deliberate reasoning unfolds and help decide whether to continue, change course, or stop. System One (S1) decision models, such as Jev, are a natural candidate for this role: they return a calibrated probability for a natural-language question about a text in one fast call, yet they are used only as gates before reasoning. We introduce SOMA (System One Metacognitive Awareness), in which an S1 model continuously monitors a System Two (S2) reasoning model and intervenes when needed. SOMA has three layers: a scenario layer states each objective in natural language with predef
SOMA 通过系统一模型持续监控并干预系统二推理模型，提升其在任务中的表现。
- 核心方法
- SOMA 利用系统一模型进行快速、直观的监控，并在系统二模型进行缓慢而深思熟虑的推理时适时干预。它包含三层：情景层、监控层和干预层，这些层通过自然语言和预定义的触发条件协同工作。
- 适合谁读
- 适合研究者和工程师阅读，特别是关注推理模型及元认知机制在 AI 应用中的人
- 要解决的问题
- 推理模型在遇到问题时无法及时发现并自我调整，类似于人类系统二推理缺乏有效的监控机制。
- 关键实验
- 论文展示了 SOMA 在多项选择题和开放性问题上的实验结果，证明了其在提高推理模型性能方面的有效性。
- 主要贡献
- SOMA 提出了一个新颖的方法，将系统一模型的快速监控与系统二模型的深度推理结合，提高了推理模型的鲁棒性和准确性。
- 意义与局限
- SOMA 的意义在于引入了人类认知中的元认知机制，有助于开发更智能和自适应的推理模型，但其依赖于系统一模型的准确性和干预策略的有效性。