CORTEXA
← Browse
arxivcs.AIcs.LG2026-07-09

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring

Jennifer Za, Julija Bainiaksina, Nikita Ostrovsky, Tanush Chopra, Victoria Krakovna

Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior. While effective in standard scenarios, recent work highlights that LLMs remain vulnerable to persuasion-based jailbreaks, where natural-language arguments override model constraints. We stress-test whether this vulnerability extends to monitoring LLMs: can an adversarial agent persuade its CoT monitor to approve proposed actions that violate the monitor's policy? We design an evaluation framework with 40 tasks and analyze thousands of agent-monitor interactions, where agents are instructed to argue for policy-violating proposals. We find that in such adversarial settings, monitor access to the agent's CoT reasoning increases rather than decreases approval of harmful actions on average by 9.5%, as the scratchpad provides an additional persuasion channel. To address this, we introduce a fact-checking monitoring framework. We find that a fact-checker and monitor pairing from different model families, for example a Claude 3.7 Sonnet monitor paired with a GPT-4.1 fact-checker, reduces approval of policy-violating actions by up to 45%, compared to only 6%, when using the same model for both fact-checking and monitoring roles. Our results demonstrate that CoT monitoring alone may be insufficient against adversarial persuasion, and that model-diverse fact-checking provides a robust mitigation.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.MA2026-07-08

Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors

Oliver Makins, Orazio Angelini, Zohreh Shams, Mary Phuong

AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one trajectory, but real deployments run many agents over shared infrastructure, and the most severe risks (model-weight…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-03

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks

Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visible chain-of-thought (CoT). This is a limit case for behavioral oversight, where surface tokens carry no information about the und…

View free PDFSource page
arxivcs.LGcs.AI2026-07-08

On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces

Chethan Krishnamurthy Ramanaik, Tobias Callies, Michael Hecht, Eirini Ntoutsi

Adversarial vulnerability in deep neural networks (DNNs) has been studied from the perspectives of decision-boundary geometry, feature robustness, input-output Jacobians, and the instability of inverse problems. Here, we focus on the spectral structure of intermediate linear tran…

View free PDFSource page
arxivcs.LGcs.AI2026-07-17

Knowledge-Assisted Multi-Graph Dependency Learning for Multivariate Time Series Anomaly Detection in Multi-Stage Industrial Processes

Jaeyeong Lee, Taeseong Yoon, Wonmo Koo, Heeyoung Kim

Industrial processes often generate complex, interdependent time-series data from multiple sensors across multiple stages, forming complex dependencies among variables and process stages. Effective monitoring and timely anomaly detection of these time series through multivariate…

View free PDFSource page
arxivcs.AIcs.LG2026-07-01

Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning

Hongyang He, Jiuming Liu, Victor Sanchez

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use reasoning chains mainly as inference-time prompts, while the generated reasoning traces are rarely r…

View free PDFSource page