Ruizhi Qian, Lei Shi, Tianyu Hu, Bo Yan, Song Wang, Yu Tian · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26793 · cited by 0 works (OpenAlex) · open-access PDF
심지어 증상이 자신의 텍스트에서 눈에 띄는 경우에도, 논리 모델은 종종 문제를 발견하지 않고, 심지어 증상이 자신의 텍스트에서 눈에 띄는 경우에도 발생합니다. 인간에서 메타코니션은 모니터링과 제어를 분리합니다 : 빠르고 직관적 인 신호는 느린 동안 시계를 유지하고, 의도적 인 논리가 발현되며 진행, 경로를 변경하거나 중지하는지 결정하는 데 도움이됩니다. 시스템 하나 (S1) 의사 결정 모델, 예를 들어 Jev,이 역할에 대한 자연적 인 후보자입니다 : 그들은 하나의 빠른 호출에서 텍스트에 대한 질문에 대한 자연 언어에 대한 진단 된 확률을 반환합니다. 그러나 그들은 사전 정의 된 행동으로 각각의 목표를 나타냅니다.
Machine translation (Meta M2M100); the English original follows.
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 predefined actions, an awareness layer lets S1 judge whether the described behavior appears, and a control layer accumulates these judgments, first reminds S2, and takes over only if the behavior persists. Sharing one S1 model and one controller across tasks, without training, SOMA addresses two different failures on two reasoning models: on overthinking, it cuts reasoning tokens by up to 36\% while improving average accuracy, and on unanswerable questions, it raises abstention from 70.5\% to 87.2\%.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Metacognition, Soma, Control (management), Natural (archaeology), Artificial intelligence
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26793, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange