arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.09043cs.AI
收藏

时间、身份与语言模型代理的意识

Time, Identity and Consciousness in Language Model Agents

Elija Perrier, Michael Timothy Bennett

AI总结:

本文提出一种基于时间间隙的框架,用于评估语言模型代理的身份持续性,通过分离成分发生与共存,建立身份形态空间并提供保守的评估工具。

摘要:

机器意识评估大多关注行为。对于语言模型代理而言,行为是语言和工具使用。这使得代理能够在约束条件不同时存在的情况下说出正确的事情。我们应用Stack Theory的时间间隙来构建轨迹。这将评估窗口内的成分发生与单个目标步骤中的共存分离。我们然后在基于身份的陈述上实例化Stack Theory的Arpeggio和Chord公理。这产生两个可以从此处仪器化的轨迹中计算出的持续性分数。我们将这些分数与五个操作性身份度量指标联系起来,并将常见轨迹映射到一个身份形态空间中,以揭示可预测的权衡。结果是一个保守的身份评估工具包。它将像稳定自我一样说话与像一个有组织的自我一样组织区分开来。

英文摘要:

Machine consciousness evaluations mostly see behavior. For language model agents that behavior is language and tool use. That lets an agent say the right things about itself even when the constraints that should make those statements matter are not jointly present at decision time. We apply Stack Theory's temporal gap to scaffold trajectories. This separates ingredient-wise occurrence within an evaluation window from co-instantiation at a single objective step. We then instantiate Stack Theory's Arpeggio and Chord postulates on grounded identity statements. This yields two persistence scores that can be computed from instrumented scaffold traces. We connect these scores to five operational identity metrics and map common scaffolds into an identity morphospace that exposes predictable tradeoffs. The result is a conservative toolkit for identity evaluation. It separates talking like a stable self from being organized like one.

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。

↑