The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way. A system can saturate capability benchmarks while remaining entirely reactive, acting only when prompted and ceasing all activity when a task completes. We introduce the Autonomous Agency Scale (AAS), a behavioral framework that scores AI systems on a 0-5 lexicon across seven dimensions of agency:
Record details
Published: 20 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Jobs & economy
Retrieved: 21 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
arXiv cs.CY · 21 July 2026
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
HuggingFace Daily Papers · 20 July 2026
Human Grounded Evaluation of Large Language Models for Optical Network Automation
arXiv cs.AI · 20 July 2026
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
arXiv · 20 July 2026
When Not to Automate: A Formal Protocol for Human Preservation in AI-Optimized Organizations
arXiv cs.CY · 20 July 2026
Understanding ADHD Productivity in Construction Work: Toward AI-enabled VR Interventions
arXiv cs.HC · 21 July 2026
How to cite this record
ethics.ai (20 July 2026), “The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems,” evidence record 12222, https://ethics.ai/record/12222 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.