A growing body of research suggests that the cognitive processes of large language models (LLMs) differ fundamentally from those of humans. However, existing interpretability methods remain limited in explaining how cognitive abilities are engaged during LLM reasoning. In this paper, we propose UniCog, a unified framework that analyzes LLM cognition via a latent mind space. Formulated as a latent variable model, UniCog encodes diverse abilities from dense model activations into sparse, disentangled latent dimensions. Through extensive analysis on six advanced LLMs, including DeepSeek-V3.2 and GPT-4o, we reveal a Pareto principle of LLM cognition, where a shared reasoning core is complemented by ability-specific signatures. Furthermore, we discover that reasoning failures often manifest as anomalous intensity in latent activations. These findings opens a new paradigm in LLM analysis, providing a cognition grounded view of reasoning dynamics. Finally, leveraging these insights, we introduce a latent-informed candidate prioritization strategy, which improves reasoning performance by up to 7.5% across challenging benchmarks. Our code is available at https://github.com/milksalute/unicog.

翻译：越来越多的研究表明，大语言模型（LLM）的认知过程与人类存在根本差异。然而，现有的可解释性方法在阐明LLM推理过程中如何调用认知能力方面仍存在局限。本文提出UniCog，一个通过潜在心智空间分析LLM认知的统一框架。该框架被构建为一个潜在变量模型，能够将密集的模型激活编码为稀疏、解耦的潜在维度，以表征多样化的能力。通过对DeepSeek-V3.2和GPT-4o等六个先进LLM的广泛分析，我们揭示了LLM认知的帕累托原则：一个共享的推理核心辅以能力特定的特征。此外，我们发现推理失败往往表现为潜在激活强度的异常。这些发现为LLM分析开辟了新的范式，提供了基于认知的推理动态视图。最后，基于这些洞见，我们提出了一种基于潜在信息的候选答案优先级排序策略，该策略在多个具有挑战性的基准测试中将推理性能提升了高达7.5%。我们的代码发布于 https://github.com/milksalute/unicog。