arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.03239cs.AI
收藏

用六只鸟投掷石头:关于代理与代理性

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

Ioannis Tsiokos

AI总结:

本文基于六鸟理论探讨代理性,提出通过类型正确的方法区分代理与代理性,通过四个可检查组件验证代理性,结果展示了代理性与代理的分离测试。

摘要:

六鸟理论(SBT)将宏观物体视为诱导闭包而非原始实体。对代理的实证讨论常将持续性(作为物体)与控制(制造反事实差异)混淆,使代理主张难以测试且易被欺骗。本文在SBT内提供类型正确的代理账户:理论诱导一层具有显式接口和账本约束的层;代理是维持的理论对象,其可行接口政策可引导外部未来,同时保持可行性。通过有限受控系统用四个可检查组件操作化此合同:账本门控可行性、作为最固定点下后续支持语义计算的稳健可行性内核、可行赋能(通道容量)作为差异制造的代理、以及一个经验包装图,其幂等缺陷量化粗略观察下的物体性。在最小环世界中,通过修复切换、协议缠绕、身份分期和操作符重写切换,匹配控制消融产生四个分离:校准的零 regime 仅含单动作显示零赋能并阻止模型规格误报;启用修复消除幂等缺陷;协议仅在两步或更多步骤的边界增加赋能;学习重写操作符单调增加中位赋能(0.73到1.34比特)。这些结果提供了可追溯测试,区分代理性与代理,不涉及目标、意识或生物体,且配有可重复、审计的制品。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑