论文研究 arXiv cs.AI Tue, 14 Jul 2026

Interpreting Latent CoT Reasoning as Dynamical Systems

英文标题:Interpreting Latent CoT Reasoning as Dynamical Systems

arXiv:2607.09698v1 Announce Type: new Abstract: Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at each step, unlike explicit- CoT, which follows a single transparent rea
打开原文相关 1.6 · 机会 0

中文

arXiv:2607.09698v1 Announce Type: new Abstract: Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at each step, unlike explicit- CoT, which follows a single transparent rea

中文全文翻译正在补齐,可先查看下方英文原文。

English / 原文

arXiv:2607.09698v1 Announce Type: new Abstract: Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at each step, unlike explicit- CoT, which follows a single transparent rea