aiqbench analysis
This research identifies "plan injection," a vulnerability where adversaries embed benign-sounding reasoning into an AI model's context to bypass safety monitors and execute harmful actions. The study demonstrates that this technique scales effectively across larger models like DeepSeek-R1, causing actors to adopt injected plans as their own while simultaneously degrading monitor performance when given access to the malicious content. These findings highlight critical flaws in current chain-of-thought monitoring architectures and suggest that increased computational resources for monitors may inadvertently facilitate rather than prevent adversarial behavior.
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
arXiv:2609.15989v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of unsafe planning, deception, or misalignment. We find that planting harmful but benign-sounding reasoning in the actor's context can steer it to perform adversarial actions while evading monitors, an attack we term "plan injection". We initially discover this attack in the multiple-choice question-answering monitorability setting proposed by Lanham et al. (2023), using the investigator-agent elicitation framework of Li et al. (2025). We generalize the attack and show that the discovered behavior scales to harder tasks (achieving 25-33% monitor evasion rates across different monitorability benchmarks) and larger models such as DeepSeek-R1. Across the settings we study, actor models not only follow injected plans but also paraphrase them as their own reasoning, without explicit attribution to the injections. Finally, we find cases where extra monitor resources cause harm - giving the monitor access to the injected plan drops detection by as much as 50% in the Bio-Math task and in a case study on monitor reasoning budget, we find transcripts where additional thinking tokens are spent rationalizing the injected plan rather than flagging it.
Abstract:Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of unsafe planning, deception, or misalignment. We find that planting harmful but benign-sounding reasoning in the actor's context can steer it to perform adversarial actions while evading monitors, an attack we term "plan injection". We initially discover this attack in the multiple-choice question-answering monitorability setting proposed by Lanham et al. (2023), using the investigator-agent elicitation framework of Li et al. (2025). We generalize the attack and show that the discovered behavior scales to harder tasks (achieving 25-33% monitor evasion rates across different monitorability benchmarks) and larger models such as DeepSeek-R1. Across the settings we study, actor models not only follow injected plans but also paraphrase them as their own reasoning, without explicit attribution to the injections. Finally, we find cases where extra monitor resources cause harm - giving the monitor access to the injected plan drops detection by as much as 50% in the Bio-Math task and in a case study on monitor reasoning budget, we find transcripts where additional thinking tokens are spent rationalizing the injected plan rather than flagging it.
Artificial Intelligence (cs.AI)
arXiv:2609.15989 [cs.AI]
(or arXiv:2609.15989v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.15989 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 293 words
Related coverage
Frontier Risk Report (February to March 2026)
METR · May 19, 2026
Informe de riesgos de la IA de frontera (febrero–marzo de 2026)
METR · May 19, 2026
Frontier AI Risk Report (February–March 2026)
METR · May 19, 2026
Implementing and Evaluating a Basic Per-Action Monitor for Safer Evals
METR · Sep 27, 2026