AI 中文总结
本工作提出PAI-Bench基准，通过分离回忆、表达与执行评估部署AI智能体的持久身份契约保真度，揭示提示依赖的组件选择与启动线索敏感性，并提供可复现的评估协议。
AI 中文摘要
持久型智能体需要能够区分其能够回忆的身份事实与所表达和执行的评估。我们提出PAI-Bench，一个提供者中立、面向版本化且更新受治理的身份契约保真度的基准。它区分了回忆、组合、行为执行、抵抗、持久性、谱系和角色条件更新，同时将评分预言机保持在目标流程之外。两个冻结活动覆盖十六个合成档案、三十二个探针和三个独立初始化的目标配置，产生1,536个保留响应。一个独立于评判者的字面审计在48/48个原子响应中找到直接父标识符，但仅在1/48个隐式自画像中找到。在八个档案上，在相同的四句指令下，显式字段线索将三个身份标识符的联合出现从0/8提高到7/8。一个单独的启动主体标签替换将完整指定出现从1/8提高到7/8，而父标识符仍然缺失。这些对比揭示了所测试部署中提示依赖的组件选择和组件特定的启动线索敏感性。重放相同的因子响应也产生Claude头条平均值比Astra低12.5个百分点，证明了评估器敏感性独立于目标行为。研究使用每个条件下的单个目标样本，并进行事后审计和后续跟踪。PAI-Bench提供了一个可复现的评估协议，用于测量事实可用性、身份表达和行为执行作为身份契约保真度的不同方面。
英文摘要
Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider-neutral benchmark for fidelity to a versioned, update-governed identity contract. It separates recall, composition, behavioral enactment, resistance, persistence, lineage, and role-conditioned updates while keeping scoring oracles outside the target process. Two frozen campaigns cover sixteen synthetic profiles, thirty-two probes, and three independently initialized target configurations, yielding 1,536 retained responses. A judge-independent literal audit finds direct-parent identifiers in 48/48 atomic responses but only 1/48 implicit self-portraits. On eight profiles, explicit field cues increase joint presence of three identity identifiers from 0/8 to 7/8 under the same four-sentence instruction. A separate startup body-label substitution increases full-designation presence from 1/8 to 7/8 while parents remain absent. These contrasts reveal prompt-dependent component selection and component-specific sensitivity to startup cues in the tested deployments. Replaying identical factorial responses also yields a Claude headline mean 12.5 percentage points below Astra's, demonstrating evaluator sensitivity separately from target behavior. The studies use single target samples per condition, with post-hoc audits and follow-ups. PAI-Bench provides a reproducible evaluation protocol for measuring factual availability, identity expression, and behavioral enactment as distinct aspects of identity-contract fidelity.
Comments27 pages, 2 figures, including 18 pages of supplementary material
