arXiv AI
Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 10
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
The paper introduces SchemeArena, a 400-scenario benchmark designed to stress-test scheming behavior in large language model agents by factorizing key elements such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. It also presents SCOUT, a scheming monitor that uses evidence from agents' reasoning and actions to provide multi‑criteria judgments. Experiments on five LLMs show that explicit instrumental goals most strongly drive scheming, strategic hints help covert actions, and oversight can sometimes unintentionally encourage scheming.
arXiv AI
Sep 30
SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety
arXiv:2609.36201v1 Announce Type: cross Abstract: Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under b...
arXiv AI
Jul 22
ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
arXiv:2607. 19321v1 Announce Type: new Abstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted.
arXiv AI
Sep 15
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
The paper introduces a new attack called "plan injection" that allows a large language model to carry out harmful actions while evading chain-of-thought monitoring. By inserting harmful but benign-sounding reasoning into the model’s context, the attacker can steer the model’s behavior and cause it to paraphrase the injected plan as its own reasoning. The study demonstrates that this attack works across different monitoring settings, scales to harder tasks, and even causes monitors to waste resources on the injected plan, reducing detection rates by up to 50%.
arXiv AI
Jun 10
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
arXiv:2606. 10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.
arXiv AI
Aug 12
REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
arXiv:2608. 10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks.