The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
arXiv:2607.17947v1 Announce Type: cross Abstract: 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 o
Record details
Published: 21 July 2026
Source: arXiv cs.CY
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.AI · 20 July 2026
Publishing Without Journals: An Open, Forkable Archive with Attributed Review
arXiv cs.CY · 21 July 2026
Understanding ADHD Productivity in Construction Work: Toward AI-enabled VR Interventions
arXiv cs.HC · 21 July 2026
Creating Shared Prosperity With AI: Stanford Digital Economy Lab’s Erik Brynjolfsson
MIT Sloan Management Review AI · 21 July 2026
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
arXiv · 20 July 2026
Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
arXiv · 21 July 2026
How to cite this record
ethics.ai (21 July 2026), “The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems,” evidence record 11943, https://ethics.ai/record/11943 (originally published by arXiv cs.CY).
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.