Can You Undo It? Reversibility Classes for AI Agent Actions

Impact 7 arXiv cs.AI

Summary

  • Researchers introduced Reversibility Classes, a declared five-level vocabulary with argument-sensitive rules and prior-state capture contracts for tool-using AI agents.
  • The implementation covers 536 tools across 20 MCP servers, with all 738 rule-case checks conforming to declared expectations.
  • Session guard experiments gated actions in 29 attack-positive runs while adding nine approval points across 1,209 benign runs.
  • Controlled experiments across files, Git, SQLite, and browsers show recovery depends on state capture, subsequent changes, and recovery routes, exposing a Git merge-state exception.

Why it matters

Understanding and classifying whether an AI agent's tool actions can be undone is critical for preventing unrecoverable errors and managing risk in autonomous execution environments.

Who should care