arXiv cs.AI· Kentaro Ozeki, Risako Ando, Takanobu Morishita, Hirohiko Abe, Koji Mineshima, Mitsuhiro Okada·· 12 小时前AI 评分45
大型推理模型是合格的日常推理者吗？与非推理模型在逻辑推理任务上的对比
Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks
AI 导读
一项基于语言与语用推理现象构建的新基准测试发现，大型推理模型在日常推理偏离形式逻辑规则时性能反而下降，部分使用 chain-of-thought 提示的非推理模型在日常推理上超过了同类推理模型。额外指令提示对推理行为的控制作用有限，表明当前推理模型无法可靠捕捉日常推理，后训练目标与评测方式仍需改进。
正文 · 原文
Abstract:Large reasoning models (LRMs) that leverage test-time computation achieve strong performance on mathematical and scientific benchmarks and are increasingly deployed in real-world applications. However, their ability to perform \textit{everyday logical reasoning}, which often departs from textbook formal logic, remains underexplored. In this work, we systematically evaluate how well reasoning models align with everyday reasoning patterns by introducing a benchmark based on linguistic and pragmatic reasoning phenomena. We also compare reasoning models with non-reasoning models under controlled prompting conditions. We find that, in many cases, (1) reasoning models show degraded performance in everyday reasoning when such reasoning deviates from formal logical rules, (2) some non-reasoning models with chain-of-thought prompting outperform comparable reasoning models in everyday reasoning, and (3) prompting with additional instructions provides limited control over reasoning behavior. These findings suggest that current reasoning models do not reliably capture everyday reasoning and point to limitations in post-training, motivating improved training objectives and evaluation across diverse forms of reasoning.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22538 [cs.AI] |
| (or arXiv:2610.22538v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22538 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kentaro Ozeki [view email]
[v1]
Thu, 15 Oct 2026 18:37:22 UTC (56 KB)
来源：arXiv cs.AI · arxiv.org