Large Reasoning Models (LRMs) are increasingly integrated into systems requiring reliable multi-step inference, yet this growing dependence exposes new vulnerabilities related to computational availability. In particular, LRMs exhibit a tendency to "overthink", producing excessively long and redundant reasoning traces, when confronted with incomplete or logically inconsistent inputs. This behavior significantly increases inference latency and energy consumption, forming a potential vector for denial-of-service (DoS) style resource exhaustion. In this work, we investigate this attack surface and propose an automated black-box framework that induces overthinking in LRMs by systematically perturbing the logical structure of input problems. Our method employs a hierarchical genetic algorithm (HGA) operating on structured problem decompositions, and optimizes a composite fitness function designed to maximize both response length and reflective overthinking markers. Across four state-of-the-art reasoning models, the proposed method substantially amplifies output length, achieving up to a 26.1x increase on the MATH benchmark and consistently outperforming benign and manually crafted missing-premise baselines. We further demonstrate strong transferability, showing that adversarial inputs evolved using a small proxy model retain high effectiveness against large commercial LRMs. These findings highlight overthinking as a shared and exploitable vulnerability in modern reasoning systems, underscoring the need for more robust defenses.

翻译：大型推理模型逐渐被集成到需要可靠多步推理的系统中，然而这种日益增长的依赖暴露了与计算可用性相关的新漏洞。特别是，当面对不完整或逻辑不一致的输入时，大型推理模型倾向于"过度思考"，产生过长且冗余的推理轨迹。这种行为显著增加了推理延迟和能耗，构成了拒绝服务式资源耗尽的潜在攻击向量。在此工作中，我们研究了这一攻击面，并提出了一种自动化黑盒框架，通过系统性扰动输入问题的逻辑结构来诱导大型推理模型过度思考。我们的方法采用基于结构化问题分解的分层遗传算法，并优化了一个复合适应度函数，旨在最大化响应长度和反思性过度思考标记。在四个最先进的推理模型上，所提方法显著放大了输出长度，在MATH基准测试中实现了高达26.1倍的增加，并始终优于良性及人工构造的缺失前提基线。我们进一步展示了强大的可迁移性，表明使用小型代理模型演化得到的对抗输入对大型商业推理模型依然保持高效。这些发现突显了过度思考作为现代推理系统中一个共有且可被利用的漏洞，强调了开发更鲁棒防御的必要性。