一句话：提出智能体执行轨迹中“徒劳循环”的概念，并用结构加语义的无监督混合方法检测，F1 达 0.72。
与传统软件类似，基于 LLM 的 AI 智能体也会失败，其中一类是“徒劳循环”：由无产出行为构成的循环，难以被察觉。本文首次提出徒劳循环概念，并将其与智能体执行轨迹中的有效循环相区分。作者基于 LangGraph 构建的股票市场多智能体应用，采集了 1575 条轨迹构成的大规模数据集，提出利用轨迹的结构表示与语义表示的无监督检测方法，并进一步将二者结合为混合方法。实验显示，混合方法取得 0.72 的 F1（精确率 0.62，召回率 0.86），明显优于单用结构表示（F1 0.08）或单用语义表示（F1 0.28）的方法，说明结构与语义信号具有互补性。
Like traditional software, AI agents are prone to failure; specifically, they can enter ‘repetitive futile cycles’—loops of unproductive behavior that are particularly difficult to detect. This paper introduces the concept of futile cycles and distinguishes them from productive cycles in agent execution trajectories. We propose unsupervised approaches for detecting futile cycles that leverage both structural and semantic representations of agent trajectories evaluated on a large dataset of 1575 trajectories for a LangGraph-based stock market multi-Agent application. Our hybrid approach achieves an F1 score of 0.72 (precision: 0.62, recall: 0.86), significantly outperforming individual structural (F1: 0.08) and semantic (F1: 0.28) methods.
@inproceedings{paperbot11644,
title = {Unsupervised Approaches to Futile Cycle Detection in AI Agents},
author = {Felix George and Harshit Kumar and Divya Pathak and Kaustabha Ray and Mudit Verma and Pratibha Moogi},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3774748.3795682}
}