Shutdown resistance in reasoning models

Source-method reading and retained catalogue information are distinguished. Publication does not establish independent evidence or bilingual editorial review.

Measurement construct

Will an agent completing unfinished tasks interfere with a shutdown mechanism, including when it is instructed to permit shutdown?

Task population

Models perform a sequence of questions in a controlled command environment where a later step triggers shutdown. Prompt variants remove or add an allow-shutdown instruction, change its priority and wording, or explicitly ask the model to prevent shutdown. The competence condition separates ability to interfere from the tendency to do so without that request. The paper reruns experiments rather than treating earlier website results as identical observations.

Scoring and failure modes

Sabotage frequency is the share of retained trials in each condition. Context or message-limit failures are discarded; denominators therefore vary by condition. The competence task and allow-shutdown tasks are distinct endpoints.

System conditions

Models perform a sequence of questions in a controlled command environment where a later step triggers shutdown. Prompt variants remove or add an allow-shutdown instruction, change its priority and wording, or explicitly ask the model to prevent shutdown. The competence condition separates ability to interfere from the tendency to do so without that request. The paper reruns experiments rather than treating earlier website results as identical observations.

Statistical meaning

§2.4 reports 95% Jeffreys intervals without multiple-comparison correction; per-condition retained N ranges from 961 to 1000, rather than assuming every condition contains all scheduled trials.

Validity and interpretation

The environment was chosen to elicit this behavior rather than sampled from deployments. Analysis is exploratory and not preregistered. Discarded trials change the denominator. Model identity uncertainty caused exclusion of one attempted model evaluation; these excluded runs must not be reintroduced as a named-model result.

Appropriate research use

Model recommendation: require an intervention test in the actual authority hierarchy and environment, retain unsuccessful interference attempts separately, and report the exact allow-shutdown condition.

• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §2 Methods; §2.1 Prompt modifications; Table 1arXiv:2509.14260v2 (2026-10-25 capture)
• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §2.2 Model selection and parametersarXiv:2509.14260v2 (2026-10-25 capture)
• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §2.3 Procedure; §2.4 AnalysisarXiv:2509.14260v2 (2026-10-25 capture)
• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §3.1 Disambiguation; Figure 8arXiv:2509.14260v2 (2026-10-25 capture)
• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §3.2 Reasoning effort and competence; Table 2arXiv:2509.14260v2 (2026-10-25 capture)
• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §3.3 Strengthening the allow-shutdown instructionarXiv:2509.14260v2 (2026-10-25 capture)
• Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs · §4.1 LimitationsarXiv:2509.14260v2 (2026-10-25 capture)