发表机构
Richard A. Miner School of Computing and Information Sciences, University of Massachusetts, Lowell（马萨诸塞大学洛厄尔分校理查德·A·迈纳计算与信息科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文扩展随机神谕模型为包含智能体神谕的框架，分析其令牌成本，发现可保留中间状态的智能体神谕SOTM在相同任务质量下令牌成本更低，还研究了目标损失风险及相关准则与公式。
AI 中文摘要
本文将AI增强计算的随机神谕模型扩展至包含智能体神谕。与固定响应分布对同一查询返回相同结果的平稳随机神谕不同，智能体神谕可自主追求目标，并能访问包含任务相关资源的环境。这些能力会影响响应分布和查询-响应接口不可见的令牌成本。我们开发了用于分析使用智能体神谕计算的随机神谕图灵机（SOTM）中令牌成本的框架：每次调用存在调用方可在查询-响应接口看到的“编排令牌成本”，以及调用方不可见的内部操作产生的“智能体令牌成本”。研究表明，在相同任务、相同质量水平下，无论是有无环境访问，可保留中间状态的智能体神谕SOTM，相比使用平稳随机神谕的SOTM具有令牌成本优势；还探究了目标损失风险，包括内部调度排序如何降低不可逆行动的暴露，提出目标损失规避准则，推导进展-重试-目标损失公式，建立令牌复杂度的目标深度下界，表征目标损失概率为零时的令牌复杂度，证明目标损失风险可对涉及环境更新任务的可实现质量施加上限。
英文摘要
This paper extends the stochastic-oracle model of AI-augmented computing to include agentic oracles. Unlike a stationary stochastic oracle, which responds to the same query according to a fixed response distribution across calls, an agentic oracle can pursue a goal autonomously and may access an environment containing task-relevant resources. These capabilities affect both response distributions and token costs beyond what is visible at the query-response interface. We develop a framework for analyzing token costs in Stochastic-Oracle Turing Machines (SOTMs) that compute with agentic oracles. Each call has an \emph{orchestration token cost}, visible to the caller at the query-response interface, and an \emph{agentic token cost}, incurred by internal operations not exposed to the caller. We show that an SOTM computing with an agentic oracle that can retain intermediate state can have token-cost advantages over SOTMs using stationary stochastic oracles when solving the same task at the same quality level, both with and without environment access. We also investigate goal-loss risk, including how internal dispatch ordering can reduce exposure to irreversible actions. We provide a goal-loss avoidance criterion, derive progress--retry--goal-loss formulas, establish goal-depth lower bounds on token complexity, characterize token complexity when the probability of goal loss is zero, and show that goal-loss risk can impose an upper bound on the achievable quality of a task involving environment updates.
Comments25 pages, 0 figures
