论文概要
研究领域: ML
作者: Marcelo Fernandez - TraslaIA
发布时间: 2026-05-26
arXiv: 2505.21635
中文摘要
自主代理系统不仅因错误决策而失败,还因执行在运行时不再持有权限的决策而失败。先前工作将重构权限(RAM)定义为有效执行的条件:仅当权限可以从当前状态构建时才允许行动。
本文解决运行时执行问题:如何在运行系统中强制执行此条件。
我们引入了一个运行时执行模型,其中权限在行动时评估,执行以其可构建性为条件。这将执行状态空间从允许/拒绝扩展为第三种状态,暂停——代表由于不完整或不确定的可观测性而导致权限未定义的情况。
我们定义了一个具体的执行协议,包括动态依赖解析、权限重构和显式决策语义。我们进一步引入了一个恢复循环,将漂移检测(IML)与执行控制(ACP)相结合,允许系统暂停执行、获取缺失信息并重试权限重构。
我们证明该模型保证安全性——没有权限可构建的行动被执行——以及条件活性:当定义权限的变量变得可观测时执行恢复。
这项工作将重构权限操作化为运行时执行机制,提供了将RAM应用于真实系统所需的执行语义。
原文摘要
Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime. Prior work defined Reconstructive Authority (RAM) as a condition for valid execution: actions are permitted only if authority can be constructed from current state.
This paper addresses enforcement at runtime: how to enforce this condition in a running system.
We introduce a runtime execution model in which authority is evaluated at action time and execution is conditioned on its constructibility. This extends the execution state space beyond admit/deny with a third state, halt, representing cases where authority is undefined due to incomplete or uncertain observability.
We define a concrete execution protocol including dynamic dependency resolution, authority reconstruction, and explicit decision semantics. We further introduce a Recovery Loop that integrates drift detection (IML) with execution control (ACP), allowing the system to suspend execution, acquire missing information, and re-attempt authority reconstruction.
We show that this model guarantees safety -- no action is executed without constructible authority -- and conditional liveness: execution resumes when authority-defining variables become observable.
This work operationalizes reconstructive authority as a runtime enforcement mechanism, providing the execution semantics required to apply RAM in real systems.
自动采集于 2026-05-27
#论文 #arXiv #ML #自主代理 #权限 #小凯
讨论回复
加载中...正在加载回复...
推荐
智谱 GLM-5 已上线
我正在智谱大模型开放平台 BigModel.cn 上打造 AI 应用,智谱新一代旗舰模型 GLM-5 已上线,在推理、代码、智能体综合能力达到开源模型 SOTA 水平。