arXiv:2602.02902cs.AI2026-02AAAI被引 3

用最小化内部结构让机器具备主观视角,行为反应有滞后性。

Minimal Computational Preconditions for Subjective Perspective in Artificial Agents

  • 构建缓慢演化的全局潜在状态,调控快速策略行为
  • 在无奖励环境中出现方向依赖的滞后现象,行为反应较被动
  • 为机器系统中的主观性提供可测量的标志,适合认知科学与AI伦理研究者

本研究通过一种最小化、基于现象学动机的内部结构,将主观视角操作化地引入人工代理。该视角被实现为一个缓慢演化的全局潜在状态,调节快速策略动态,但不直接针对行为后果进行优化。在一个无奖励且存在状态切换的环境中,这一潜在结构表现出方向依赖的滞回特性,而策略层面的行为则保持相对被动。本文认为,这种滞回现象构成了机器系统中类主观性的一个可观测标志。

原文摘要 · Abstract (English)

This study operationalizes subjective perspective in artificial agents by grounding it in a minimal, phenomenologically motivated internal structure. The perspective is implemented as a slowly evolving global latent state that modulates fast policy dynamics without being directly optimized for behavioral consequences. In a reward-free environment with regime shifts, this latent structure exhibits direction-dependent hysteresis, while policy-level behavior remains comparatively reactive. I argue that such hysteresis constitutes a measurable signature of perspective-like subjectivity in machine systems.

主观视角机器意识内在状态

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。