Saved in:
Bibliographic Details
Main Authors: Zheng, Yusheng, Yang, Yiwei, Zhang, Wei, Quinn, Andi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.20625
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • LLM agent frameworks increasingly offer checkpoint-restore for error recovery and exploration, advising developers to make external tool calls safe to retry. This advice assumes that a retried call will be identical to the original, an assumption that holds for traditional programs but fails for LLM agents, which re-synthesize subtly different requests after restore. Servers treat these re-generated requests as new, enabling duplicate payments, unauthorized reuse of consumed credentials, and other irreversible side effects; we term these semantic rollback attacks. We identify two attack classes, Action Replay and Authority Resurrection, validate them in a proof of concept experiment, and confirm that the problem has been independently acknowledged by framework maintainers. We propose ACRFence, a framework-agnostic mitigation that records irreversible tool effects and enforces replay-or-fork semantics upon restoration