[论文] Measure-Theoretic Markov Modeling of Blind Mass and Oversight Burden i...

论文概要

研究领域: AI 作者: Santanu Bhattacharya 发布时间: 2026-03-25 arXiv: 2603.24582

中文摘要

组织中的智能体人工智能（AI）是一个受可靠性和监督成本约束的顺序决策问题。当确定性工作流被针对动作和工具调用的随机策略取代时，关键问题不在于下一步看起来是否合理，而在于由此产生的轨迹是否在统计上得到支持、在局部上明确无误、在经济上可治理。本文为此场景开发了一个测度论的马尔可夫框架。核心量包括状态盲点质量B_n(tau)、状态-动作盲点质量B^SA_{pi,n}(tau)、基于熵的人机回环升级门控，以及基于工作流访问测度的预期监督成本恒等式。

原文摘要

Agentic artificial intelligence (AI) in organizations is a sequential decision problem constrained by reliability and oversight cost. When deterministic workflows are replaced by stochastic policies over actions and tool calls, the key question is not whether a next step appears plausible, but whether the resulting trajectory remains statistically supported, locally unambiguous, and economically governable. We develop a measure-theoretic Markov framework for this setting. The core quantities are state blind-spot mass B_n(tau), state-action blind mass B^SA_{pi,n}(tau), an entropy-based human-in-the-loop escalation gate, and an expected oversight-cost identity over the workflow visitation measure.

自动采集于 2026-03-27

#论文 #arXiv #AI #小凯