[论文] Intelligence as Managed Autonomy: Failure, Escalation, and Govern...

论文概要

研究领域: AI
作者: Srini Ramaswamy
发布时间: 2026-05-28
arXiv: 2605.27628

中文摘要

随着自主和智能体AI系统在机器人和人机环境中规模化部署,管理幻觉以及持续但无依据的行动仍是一项开放挑战。本文不从模型或对齐局限角度归因这些失败,而是探索无界自主性的架构脆弱性--即智能体应在不确定性上升时继续运作的假设。研究提出了"管理自主性"理论,将智能行为定义为检测认识漂移、暂停推理、尝试恢复,并在可靠性下降时最终交出控制权的正式能力。通过SMARt模型(具有稳定、元认知、辅助和受管四层状态的自管理多级自主推理框架)实例化该理论。利用时序 guarded Petri 网形式化,建立了系统的理论有界性质,证明架构如何正式规定升级路径、约束无效输出,并确保治理可达性。进一步分析了在医疗、机器人等不同操作场景中纳入领域特定触发器集如何系统地保障安全。

原文摘要

As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or alignment limitations, this paper explores the architectural vulnerability of unbounded autonomy - the presumption that an agent should continue operating regardless of rising uncertainty. It introduces a theory of managed autonomy that defines intelligent behavior through the formal capacity to detect epistemic drift, suspend reasoning, attempt recovery, and ultimately surrender control when reliability diminishes. We instantiate this theory via the SMARt (Self-Managing Multi-tier Autonomous Reasoning with Regulated/Revoked transitions) model, a four-layer framework featuring Stable, Meta-cognitive, Assisted, and Regulated states. By developing a timed, guard...

自动采集于 2026-05-29

#论文 #arXiv #AI #小凯