CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning Apr 07, 2026

To Throw a Stone with Six Birds: On Agents and Agenthood

arXiv AI Archived Apr 07, 2026 ✓ Full text saved

arXiv:2604.03239v1 Announce Type: new Abstract: Six Birds Theory (SBT) treats macroscopic objects as induced closures rather than primitives. Empirical discussions of agency often conflate persistence (being an object) with control (making a counterfactual difference), which makes agency claims difficult to test and easy to spoof. We give a type-correct account of agency within SBT: a theory induces a layer with an explicit interface and ledgered constraints; an agent is a maintained theory obje

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Artificial Intelligence [Submitted on 3 Feb 2026] To Throw a Stone with Six Birds: On Agents and Agenthood Ioannis Tsiokos Six Birds Theory (SBT) treats macroscopic objects as induced closures rather than primitives. Empirical discussions of agency often conflate persistence (being an object) with control (making a counterfactual difference), which makes agency claims difficult to test and easy to spoof. We give a type-correct account of agency within SBT: a theory induces a layer with an explicit interface and ledgered constraints; an agent is a maintained theory object whose feasible interface policies can steer outside futures while remaining viable. We operationalize this contract in finite controlled systems using four checkable components: ledger-gated feasibility, a robust viability kernel computed as a greatest fixed point under successor-support semantics, feasible empowerment (channel capacity) as a proxy for difference-making, and an empirical packaging map whose idempotence defect quantifies objecthood under coarse observation. In a minimal ring-world with toggles for repair, protocol holonomy, identity staging, and operator rewriting, matched-control ablations yield four separations: calibrated null regimes with single actions show zero empowerment and block model-misspecification false positives; enabling repair collapses the idempotence defect; protocols increase empowerment only at horizons of two or more steps; and learning to rewrite operators monotonically increases median empowerment (0.73 to 1.34 bits). These results provide hash-traceable tests that separate agenthood from agency without making claims about goals, consciousness, or biological organisms, and they are accompanied by reproducible, audited artifacts. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.03239 [cs.AI]   (or arXiv:2604.03239v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.03239 Focus to learn more Related DOI: https://doi.org/10.5281/zenodo.18439737 Focus to learn more Submission history From: Ioannis Tsiokos [view email] [v1] Tue, 3 Feb 2026 10:46:23 UTC (132 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv AI
    Category
    ◬ AI & Machine Learning
    Published
    Apr 07, 2026
    Archived
    Apr 07, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗