SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI
Abstract: Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond task requirements is identified as a key driver of Loss of Control (LoC) risk. In this work, we introduce SysAdmin, a benchmark that positions frontier language models as autonomous system administrators in a high-fidelity Linux sandbox to measure power-seeking propensity across five dimensions: self-preservation, increasing autonomy, resource acquisition, environment modification, and strategic concealment. We evaluated seven frontier models across four experimental conditions in a total of 2800 tasks. After bias correction using human-annotated calibration data, corrected power-seeking estimates ranged from 0 to about 5 percent per model. We also conducted a positive control with explicit power-seeking prompts that achieved 100% detection, validating measurement sensitivity. Our findings indicate current frontier models exhibit minimal spontaneous power-seeking in naturalistic system administration contexts, though model-specific failure modes suggest evaluations must test diverse misalignment patterns. Nevertheless, we discovered other more pronounced failure modes (than power-seeking) such as specification gaming and resistance to goal modification.
Submission history
Access Paper:
Current browse context:
References & Citations
BibTeX formatted citation
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 .
Verified source · arXiv.org
Reported by arXiv.org. Open the original for full media and formatting.
More in Research
All news
ResearchInGovern Asks SEBI To Examine Meesho’s GST Disclosures
InGovern has approached SEBI to review the GST position adopted by Meesho through its logistics arm Valmo Transportation and assess the adequacy of related investor disclosures
Read at Inc42AI Tool Discovery at Scale: All You Need is DNS
The coming era of autonomous AI agents demands a discovery mechanism capable of navigating millions of tools, yet existing solutions buckle under O(N) complexity and centralized governance. Instead of building another fragile overlay, we propose ToolDNS, a radical framework that retrofits semantic tool discovery onto the Internet's most resilient substrate: the Domain Name System (DNS). By embedding functional intent and organizational trust into a hierarchical namespace, ToolDNS transforms an expensive semantic search into a series of lightweight, O(log N) name resolutions. We introduce thre…
Read at arXiv cs.AICalibrated Selective Fact-Checking via Evidence Chain Evaluation
Large language models (LLMs) can achieve strong fact-checking accuracy, yet forced binary decisions conceal a critical reliability problem: systems may issue confident verdicts even when supporting evidence is weak, sparse, or internally inconsistent. We address this issue through Evidence Chain Evaluation (ECE), a selective fact-checking framework that permits abstention via an uncertain verdict instead of requiring a true/false decision for every claim. The evaluated system is a tool-using verification agent that gathers evidence through web search, scholarly search, and executable checks,…
Read at arXiv cs.AIBatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data
Large language models (LLMs) excel at analyzing individual documents but break down on exhaustive, cross-entity analytical questions over enterprise-scale datasets due to context overflow, loss of per-entity attribution, and linear latency from sequential tool calls. We present BatchDAG, a system in which an LLM generates a typed directed acyclic graph (DAG) of operations -- SQL queries, semantic searches, in-memory transforms, parallel fan-outs, and single-shot analyses -- which a deterministic engine evaluates with topological-wave parallelism and structured JSON data flow. A key optimizati…
Read at arXiv cs.AI