The paper introduces OverThink, a slowdown attack that forces reasoning language models (RLMs) to produce many more reasoning tokens while still giving correct answers. By injecting decoy reasoning problems—such as Markov decision processes, language translation, or graphic comprehension—into the model’s context, attackers can dramatically increase token generation (up to 46× on SQuAD and 17× on coding agents). The study evaluates the attack on both proprietary and open-source RLMs across multiple datasets, explores multimodal and coding‑agent variants, and tests several defenses, concluding that defending against OverThink is challenging and that newer RLMs are even more vulnerable due to higher per‑token costs and increased reasoning token usage.
By Abhinav Kumar, Jaechul Roh, Ali Naseh, Marzena Karpinska, Mohit Iyyer, Amir Houmansadr, Eugene Bagdasarian
SAVeR$^2$ is a safety alignment method for Large Reasoning Models that decomposes safety objectives into four fine‑grained verifiable reward signals and uses a difficulty‑aware data selection strategy to stabilize training. It introduces a reasoning‑preserving gradient projection mechanism that resolves conflicts between safety and reasoning gradients, eliminating the safety tax. Experiments on models from 1.5B to 671B show that SAVeR$^2$ improves safety performance and reduces over‑refusal rates without harming general reasoning abilities.
By Yichen Sun, Qirui Liu, Yan Wang, Jianan Lin, Linbo Jiang, Shiyu Wang, Zhibo Wang, Zhixuan Chu
arXiv:2506. 07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities.
By Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, Zhifang Sui
arXiv:2604. 23270v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs).
By Shuxu Chen, Yitian Zhou, Jiaquan Zhang, Haoyu Bian, Wenrui Hu, Aming Wu, Sungyoung Lee, Chaoning Zhang, Hyundong Shin
arXiv:2609.08186v1 Announce Type: new
Abstract: The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed...
By Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang, Bairui Zhang, Jia-Chen Zhang, Shaohua Li
arXiv:2609.36254v1 Announce Type: new
Abstract: Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning bef...
By Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan, Alexander Kotov, Dongxiao Zhu
arXiv:2609.22228v1 Announce Type: cross
Abstract: Large language models increasingly rely on long chain-of-thought (CoT) trajectories for complex reasoning, but autoregressive generation brings subst...
By Shaolong Chen, Ang Li, Mingjie Li, Yisen Wang
arXiv:2608. 09542v1 Announce Type: cross Abstract: Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs.
By Hongli Shen, Shaopeng Fu, Qinbo Zhang, Jian Li, Di Wang
arXiv:2607. 20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question?
By Roman Belaire, Arunesh Sinha, Pradeep Varakantham
arXiv:2503. 15560v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit harmful or unauthorized responses.
By Prashant Kulkarni, Assaf Namer
Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.
Large reasoning models generate chain-of-thought (CoT) before answering but struggle with safety alignment and can be misled by flawed premises. The paper introduces RECAP, a reinforcement learning approach that trains models to override flawed reasoning paths and produce safe, helpful responses without extra training cost. RECAP improves safety, jailbreak robustness, and reduces overrefusal while preserving core reasoning abilities and inference token budget.
By ShengYun Peng, Pin-Yu Chen, Eric Smith, Song Jiang, Hongyuan Zhan, Haozhu Wang, Mahesh Pasupuleti, Duen Horng Chau, Jianfeng Chi