科研速览 · Science Skim继续刷下去 · Keep skimming →
◆ Proceedings of the National Academy of Sciences2025-11-19· Cognition

The cost of thinking is similar between large reasoning models and humans

Andrea Gregor de Varda, Ferdinando Pio D’Elia, Hope Kean, Andrew K. Lampinen, Evelina Fedorenko

原始摘要(英文原文)· Original abstract
Do neural network models capture the cognitive demands of human reasoning? Across seven reasoning tasks, we show that the length of the chain-of-thought generated by large reasoning models predicts human reaction times both within tasks-tracking item-level difficulty-and across tasks-capturing broader differences in cognitive demands. This model-to-human alignment shows that out-of-the-box reasoning models reflect core features underlying problem and task complexity in human cognition, without requiring any built-in symbolic mechanisms.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

The cost of thinking is similar between large reasoning models and humans — 科研速览 Science Skim