arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13222cs.CCcs.AIcs.FL
收藏

代理系统可计算性

Computability of Agentic Systems

Chatavut Viriyasuthee

AI总结:

本文提出Quest图框架,分析代理系统在有限上下文下的计算能力,揭示不同模型的计算复杂度及性能差异。

摘要:

本文介绍了Quest图,一种用于分析有限上下文代理系统能力的形式框架。我们定义了抽象模型,用于建模常见的推理技术,并确立其计算能力:基础的Quest图等价于非限制型图灵机;单向的有限Quest决策过程(FQDP),尽管广泛使用,仅等价于下推自动机(上下文无关);而参考增强型QDP(RQDP)在允许状态查询时才能恢复图灵完备性。由于可计算性影响效率,我们随后通过在计算图中模拟任务依赖性来分析每个模型的理论效率。我们展示了这种计算层次结构转化为具体的性能权衡:参考增强型(图灵完备)系统在模拟复杂图时可以比非增强型(上下文无关)系统高效得多。本工作提供了一种正式的方法,用于分类和理解代理系统的基本能力。

英文摘要:

This paper introduces the Quest Graph, a formal framework for analyzing the capabilities of agentic systems with finite context. We define abstractions that model common reasoning techniques and establish their computational power: the base Quest Graph is equivalent to an unrestricted Turing machine; the forward-only Finite Quest Decision Process (FQDP), despite its wide use, is only equivalent to a pushdown automaton (context-free); and the Reference-Augmented QDP (RQDP) regains Turing completeness only when stateful queries are allowed. Since computability affects efficiency, we then analyze the theoretical efficiency of each model by simulating task dependencies in computation graphs. We show that this computational hierarchy translates to concrete performance trade-offs: reference-augmented (Turing-complete) systems can be exponentially more efficient at simulating complex graphs than their non-augmented (context-free) counterparts. This work provides a formal methodology for classifying and understanding the fundamental capabilities of agentic systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑