何时介入？关于大语言模型智能体错误与自我恢复的实证研究

# When to Intervene? An Empirical Study of Errors and Self-Recovery in LLM Agents
Source: [https://arxiv.org/abs/2610.36471](https://arxiv.org/abs/2610.36471)
[View PDF](https://arxiv.org/pdf/2610.36471)[HTML \(experimental\)](https://arxiv.org/html/2610.36471v1)

> Abstract:LLM agents interact with Web services to perform tasks on users' behalf\. Errors during these interactions can disrupt execution and prevent task completion, motivating external intervention\. However, agents may self\-recover through continued execution, raising the question of when to intervene and when to wait for self\-recovery\. We present an empirical study of errors and self\-recovery in LLM agents\. We construct ReInBench, a dataset containing 1,259 agent traces and 1,403 error events across computer\-use and Web tasks\. Our study examines how often and how quickly agents self\-recover, how self\-recovery relates to subsequent execution and task completion, and whether self\-recovery can be predicted when an error occurs\. We find that 725 error events self\-recover, often within a few steps, with self\-recovery performance differing across Execution LLMs\. Self\-recovery can also help agents recover from subsequent errors of the same type and support overall task completion\. Intervention should therefore prioritize errors unlikely to self\-recover, while allowing agents to continue when self\-recovery is likely\. Building on these empirical findings, we propose ReCoF, a method that predicts whether an error will self\-recover to inform whether additional intervention is needed\. ReCoF achieves an average relative improvement of 9\.02% in Macro\-F1 over the strongest baseline on ReInBench\. Our code and data can be found at[this https URL](https://method-notes.github.io/ReCoF/)\.

## Submission history

From: Chiming Duan \[[view email](https://arxiv.org/show-email/45a1b654/2610.36471)\] **\[v1\]**Tue, 27 Oct 2026 01:26:53 UTC \(4,063 KB\)