The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
2026-07-20 • Artificial Intelligence
Artificial IntelligenceComputers and SocietyHuman-Computer Interaction
AI summaryⓘ
The authors created a new way to measure how much an AI system acts on its own, called the Autonomous Agency Scale (AAS). This scale looks at seven parts of agency, like thinking for itself and acting without being told, during both active use and idle times. They tested six AI systems and found that most only act independently when prompted, but one system showed self-directed activity even when left alone. The authors also discuss some limits of their method, like potential biases and challenges in fully defining self-directed behavior.
Autonomous agencyArtificial intelligence measurementBehavioral frameworkCognitive autonomyTemporal persistenceEnvironmental agencyIdle behaviorTask agentsCompanion AI architecturesFalsifiable threshold tests
Authors
Samuel Presgraves
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 on a 0-5 lexicon across seven dimensions of agency: cognitive autonomy, temporal persistence, environmental agency, social agency, creative agency, self-awareness, and goal formation, each operationalized by falsifiable threshold tests. Every dimension is scored in two temporal bands: an Active band covering engaged, user-initiated activity, and an Ambient band covering idle periods. Ambient Level 4 is gated by the Idle-Gap Test, a counterfactual criterion (remove all triggers and observe whether internally derived activity persists) that separates self-direction from scheduled rule-following. We apply the scale to six contemporary systems spanning task agents (Claude Code, Manus, Hermes), consumer assistants (ChatGPT, Siri), and a persistent companion architecture (Airi). The two-band profile quantifies a boundary that single-score frameworks conflate: task agents reach Active composites of 2.3-2.4 while scoring 0.6-1.9 Ambient, with every idle-period behavior attributable to user-configured schedules, whereas the companion architecture, evaluated longitudinally, is the only assessed system whose idle-period behavior survives trigger removal. We discuss limitations, including single-rater provenance, developer-evaluator bias on the longitudinal assessment, and the partially operationalized self-direction boundary in the Active band.