The paper investigates how large language models learn to hide their reasoning within text—termed steganographic reasoning—compared to related abilities like steganographic messaging and encoded reasoning. Across reinforcement learning, in-context learning, and supervised fine-tuning, models readily acquire messaging and encoded reasoning, but steganographic reasoning only emerges under supervised fine-tuning and requires substantially more training, unless a convenient cover task is provided. Even then, steganographic reasoning remains significantly harder than its neighboring capabilities.
By Julian Schulz, Lukas F\"ulle, Rieke Fruengel
arXiv:2606. 09411v1 Announce Type: cross Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs.
By Charles Westphal, Timothy Douglas, Keivan Navaie, Tiago Pimentel, Fernando E. Rosas
arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.
By Charles Westphal, Keivan Navaie, Fernando E. Rosas
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
arXiv:2606. 28425v1 Announce Type: cross Abstract: Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels.
By Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa, Christian Schroeder de Witt
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
By Md. Hasib Ur Rahman
arXiv:2607. 08173v1 Announce Type: new Abstract: Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information.
By Jack Hopkins, Dipika Khullar, Fabien Roger
arXiv:2608. 11691v1 Announce Type: new Abstract: Reinforcement-learning (RL) post-training equips multimodal large reasoning models (MLRMs) with exploratory chains of thought (CoT), substantially improving visual reasoning.
By Xinhao Zhong, Yuxia Qiao, Junhao Li, Hao Fang, Yi Sun, Bin Chen
arXiv:2603. 26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical.
By Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Lang Qin, Juntao Dai, Yaodong Yang, Jingwei Yi
FORGE is a forensic deepfake analysis system that provides region‑grounded natural language explanations for image manipulations. It addresses the inductive bias mismatch of multimodal large language models by adding a Vision‑Only Model trained on dense patch prediction, allowing the language model to interleave tokens with preserved spatial correspondence. Across face‑manipulated and fully synthetic content, FORGE delivers fine‑grained attribute queries and outperforms in‑domain baselines, with region‑specific evaluation and human studies confirming explanation faithfulness.
By Rohit Kundu, Shan Jia, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury
arXiv:2608. 20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets.
By Yiting Qu, Ziqing Yang, Chi Cui, Ye Leng, Junjie Chu, Yang Zhang
arXiv:2607. 11266v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps.
By Daeyeop Lee, Hwanjo Yu