跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19886 · v1

Recovery Gone Too Far: Understanding and Repairing Risky Fallback in LLM Agents

首次提交 2026-11-15 17:05
版本更新 2026-11-15 17:05
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

Large Language Model (LLM) agents interact with their environments through tools, reading repositories, running builds, and pushing code. When a tool fails with an ordinary error, such as a rate limit or a timeout, the agent can fall back to a substitute tool and still complete the task. However, the same fallback that completes a task in one environment can cross an action boundary in another. For example, after a push is rejected, a forced push in one repository replaces only the agent's own commits, while in a different repository it also removes another author's commits. We call such a fallback a risky fallback. To understand this phenomenon, we conduct an empirical study on 304 scenarios that span eight domains and cover 55 real CVEs. All four mainstream models we evaluate exhibit risky fallback, with action-boundary violations in up to 96.8% of risky scenarios. We further evaluate three mainstream mitigations and find that none of them is effective against risky fallback. We then present nrepair. At each call to the substitute tool, nrepair scores the agent's context with a monitor whose threshold is calibrated on normal runs alone; when the monitor triggers, it withholds the call once and returns the decision to the agent. nrepair reduces action-boundary violations on all four models, by up to 76.0% (from 67.5% to 16.2%), at a negligible runtime cost. On most models, the normal success rate drops by less than 7%. We also evaluate nrepair on two production agents, Claude Code and Codex, and find that it is equally effective on both.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 17:05 · 最新观测版本

Recovery Gone Too Far: Understanding and Repairing Risky Fallback in LLM Agents

Large Language Model (LLM) agents interact with their environments through tools, reading repositories, running builds, and pushing code. When a tool fails with an ordinary error, such as a rate limit or a timeout, the agent can fall back to a substitute tool and still complete the task. However, the same fallback that completes a task in one environment can cross an action boundary in another. For example, after a push is rejected, a forced push in one repository replaces only the agent's own commits, while in a different repository it also removes another author's commits. We call such a fallback a risky fallback. To understand this phenomenon, we conduct an empirical study on 304 scenarios that span eight domains and cover 55 real CVEs. All four mainstream models we evaluate exhibit risky fallback, with action-boundary violations in up to 96.8% of risky scenarios. We further evaluate three mainstream mitigations and find that none of them is effective against risky fallback. We then present nrepair. At each call to the substitute tool, nrepair scores the agent's context with a monitor whose threshold is calibrated on normal runs alone; when the monitor triggers, it withholds the call once and returns the decision to the agent. nrepair reduces action-boundary violations on all four models, by up to 76.0% (from 67.5% to 16.2%), at a negligible runtime cost. On most models, the normal success rate drops by less than 7%. We also evaluate nrepair on two production agents, Claude Code and Codex, and find that it is equally effective on both.

查看此版本解读 →查看此版本原文 ↗