大型语言模型的推理缺陷

Large Language Model Reasoning Failures

February 5, 2026

作者: Peiyang Song, Pengrui Han, Noah Goodman

cs.AI

摘要

大型语言模型（LLMs）已展现出卓越的推理能力，在广泛任务中取得令人瞩目的成果。然而即便在看似简单的场景中，显著的推理缺陷依然存在。为系统化理解并解决这些不足，我们首次推出专注于LLM推理失败的综合研究综述。我们提出一种新型分类框架，将推理区分为具身与非具身两种类型，其中非具身推理进一步细分为非形式化（直觉性）推理与形式化（逻辑性）推理。同时，我们沿互补维度将推理失败归为三类：广泛影响下游任务的LLM架构固有根本性缺陷、在特定领域显现的应用场景局限性，以及因细微变动导致性能波动的鲁棒性问题。针对每类推理失败，我们明确定义、分析现有研究、探究根本原因并提出改进策略。通过整合碎片化研究，本综述为LLM系统性推理弱点提供了结构化视角，为构建更强健、可靠且具备鲁棒性的推理能力指明研究方向。我们同步发布了关于LLM推理失败的专题研究集合，可通过GitHub仓库（https://github.com/Peiyang-Song/Awesome-LLM-Reasoning-Failures）获取，为该领域研究提供便捷入口。

English

Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reasoning failures persist, occurring even in seemingly simple scenarios. To systematically understand and address these shortcomings, we present the first comprehensive survey dedicated to reasoning failures in LLMs. We introduce a novel categorization framework that distinguishes reasoning into embodied and non-embodied types, with the latter further subdivided into informal (intuitive) and formal (logical) reasoning. In parallel, we classify reasoning failures along a complementary axis into three types: fundamental failures intrinsic to LLM architectures that broadly affect downstream tasks; application-specific limitations that manifest in particular domains; and robustness issues characterized by inconsistent performance across minor variations. For each reasoning failure, we provide a clear definition, analyze existing studies, explore root causes, and present mitigation strategies. By unifying fragmented research efforts, our survey provides a structured perspective on systemic weaknesses in LLM reasoning, offering valuable insights and guiding future research towards building stronger, more reliable, and robust reasoning capabilities. We additionally release a comprehensive collection of research works on LLM reasoning failures, as a GitHub repository at https://github.com/Peiyang-Song/Awesome-LLM-Reasoning-Failures, to provide an easy entry point to this area.