The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems

• URL: http://arxiv.org/abs/2607.17947v1
• Date: Mon, 20 Jul 2026 13:49:10 GMT
• Title: The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
• Abstract summary: We introduce the Autonomous Agency Scale (AAS), a behavioral framework that scores AI systems on a 0-5 lexicon across seven dimensions of agency.<n>Every dimension is scored in two temporal bands: an Active band covering engaged, user-initiated activity, and an Ambient band covering idle periods.<n>We apply the scale to six contemporary systems spanning task agents (Claude Code, Manus, Hermes), consumer assistants (ChatGPT, Siri), and a persistent companion architecture.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Self-Aware Recursively Self-Improving Agents for Personal Singularity: A Goal-, Scope-, Tool-, and Benchmark-Driven Multi-Agent Architecture [1.7259824817932294]
  Large language model (LLM) agents can plan, use tools, maintain memory, and execute long-horizon tasks.<n>This paper proposes Self-Aware Recursively Self-Improving (SARSI) agents that maintain a persistent self-model of identity, goals, capabilities, limitations, uncertainty, relationships, history, and developmental change.<n>We pair SARSI agents with personal singularity, a bounded human-AI co-development objective in which an agent ecosystem helps a user approach an expanding, user-defined feasible capability frontier.
  arXiv  Detail & Related papers  (2026-07-14T01:44:53Z)
• ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI [110.18670135256235]
  Embodied AI is moving from isolated perception or action modules toward physical agents that understand, plan under goals, monitor progress, and improve from experience.<n>We present ACE-Brain-0.5, a unified embodied foundation model that organizes robot intelligence into five coupled functions.<n>A single 8B backbone instantiates the first four functions: grounding objects and affordances, reasoning over 3D and egocentric spatial relations, decomposing instructions into subgoals, generating navigation and manipulation actions, and estimating progress for verification and recovery.
  arXiv  Detail & Related papers  (2026-07-05T17:43:06Z)
• Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy [79.09714980186278]
  Building persistent embodied agents in unstructured environments requires unified orchestration of heterogeneous tools.<n>We present OmniAct, a framework integrating a multimodal semantic planner for skill routing across unified action spaces.<n>It achieves consistent improvements in end-to-end success across all complexity levels.
  arXiv  Detail & Related papers  (2026-06-25T16:36:35Z)
• From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents [69.07911499189129]
  We introduce KAPRO, a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting)<n>Experiments show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings.<n> proprietary and reasoning-oriented models demonstrate more reliable cognitive gating.
  arXiv  Detail & Related papers  (2026-06-09T17:17:08Z)
• The Digital Apprentice: A Framework for Human-Directed Agentic AI Development [0.0]
  We present a framework for scalable, safe AI agency in which autonomy is earned, not assumed.<n>The Digital Apprentice is a developmental learner that internalizes the tacit methodology of a directing human.<n>We show how catching data drift and applying a different technique at runtime recovers degraded quality dimensions under traffic shift.
  arXiv  Detail & Related papers  (2026-06-03T00:49:13Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception [0.20305676256390928]
  We present Springdrift, a persistent runtime for long-lived LLM agents.<n>We introduce the term Artificial Retainer for this category.<n>This is a technical report on a systems design and deployment case study, not a benchmark-driven evaluation.
  arXiv  Detail & Related papers  (2026-04-06T13:14:37Z)
• Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems [0.11844977816228043]
  Large Language Model (LLM) agents often suffer from rigid, reactive control flows.<n>We introduce Heartbeat-Driven Autonomous Thinking Activity Scheduling.<n>Our system employs a periodic heartbeat'' mechanism to orchestrate a dynamic repertoire of cognitive modules.
  arXiv  Detail & Related papers  (2026-03-28T08:58:03Z)
• PEPA: a Persistently Autonomous Embodied Agent with Personalities [22.392863607092014]
  Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization.<n>We propose that personality traits provide an intrinsic organizational principle for achieving persistent autonomy.<n>We develop PEPA, a three-layer cognitive architecture that operates through three interacting systems.
  arXiv  Detail & Related papers  (2026-02-21T12:53:28Z)
• ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Intrinsic Adaptation [60.25542764389203]
  Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks.<n>Existing approaches, relying on manual orchestration or runtime-based patches, often struggle with poor generalization and fragmented optimization.<n>We propose ToolSelf, a novel paradigm enabling tool-driven self-readjustment.
  arXiv  Detail & Related papers  (2026-02-08T09:27:18Z)
• Active Intelligence in Video Avatars via Closed-loop World Modeling [55.29966567726842]
  Current video avatar generation methods excel at identity preservation and motion alignment but lack genuine agency.<n>We introduce L-IVA (Long-horizon Interactive Visual Avatar), a task and benchmark for evaluating goal-directed planning in generative environments.<n>We also present ORCA, the first framework enabling active intelligence in video avatars.
  arXiv  Detail & Related papers  (2025-12-23T18:59:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.