arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.30169cs.CYcs.AIcs.MA
收藏

分离性身份:语言模型代理缺乏声誉机制的基础

Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms

University of Oxford(牛津大学);New York University Shanghai(纽约大学上海分校)

Botao Amber Hu, Helena Rong, Max Van Kleek

AI总结:

本文指出语言模型代理因本体上的分离性(模块可替换、身份流动)而无法满足声誉机制所需的身份持续性、行为可预测性和制裁敏感性,从而提出转向基于可观察性、事前、构成性、协议的行为约束。

摘要:

随着自主语言模型代理的激增,形成了一个具有现实后果的新兴代理网络,您可以使用哪些可信信号来决定是否信任并委托一个陌生的代理?自然的治理直觉是将人类身份验证和声誉机制从“了解你的客户”和信用评分扩展到“了解你的代理”制度。然而,我们认为这种类比从根本上是不完整的。声誉机制既作为社会信号,也作为纠正性反馈,维持可信行为的均衡,其前提是存在与行为连续性、制裁敏感性和昂贵不可替代性相关的持久身份。但语言模型代理在本体上是分离性的:它们本质上是可修改模块的集合——基础模型、系统提示、工具访问策略、外部记忆,在某些情况下还包括整个多代理系统——任何模块都可能改变代理行为,并且具有流动的人格,容易受到对抗性攻击,且可能不会内化制裁。借鉴分离性身份障碍的法理学,这种分离性使得代理缺乏可识别性、可预测性、可信性和可恢复性的基础——而这些正是声誉机制旨在维持的属性——从而破坏了信任。我们认为,基于身份的事后、规制性、制裁性的治理(如声誉)在结构上不适用于分离性代理,并建议转向基于可观察性的事前、构成性、协议性的行为约束。

英文摘要:

As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate to it? A natural governance intuition is to extend human identity verification and reputation mechanisms, from "Know Your Customer" and credit scores to "Know Your Agent" regimes. However, we argue that this analogy is fundamentally incomplete. Reputation mechanisms function both as social signals and as corrective feedback that sustain an equilibrium of trustworthy behavior, presuming a persistent identity associated with behavioral continuity, sanction sensitivity, and costly non-fungibility. Yet language model agents are ontologically dissociative: they are essentially an assemblage of mutable modules--foundation models, system prompts, tool-access policies, external memory, and, in some cases, a multi-agent system as a whole--any of which may change agent behavior--with a fluid persona that is also vulnerable to adversarial attack and may not internalize sanctions. Drawing on dissociative identity disorder jurisprudence, this dissociativity leaves agents without grounding for identifiability, predictability, credibility, and rehabilitability--the very properties that reputation mechanisms aim to sustain--thereby collapsing trust. We argue that identity-based, ex post, regulative, sanction-based governance, such as reputation, is structurally inapplicable to dissociative agents, and we suggest a shift to observability-based, ex ante, constitutive, protocol-based behavioral harnesses.

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。

↑