cs.AINov 17, 2026

Can You Undo It? Reversibility Classes for AI Agent Actions

Authors: Deepak Waghmare, Shaad Sufi

Organizations: Two Much Labs, Singapore

Abstract

Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabulary with argument-sensitive rules, conservative defaults and an explicit prior-state capture contract. The pinned implementation and evidence-linked registry cover 536 tools across 20 MCP servers. All 738 rule-case checks conform to declared expectations, while native annotation mapping differs from draft registry labels for 118 of 481 comparable tools. One AI-assisted reviewer approves 148 ratings, 75 matching the registry; this is not independent agreement. On 2,158 recorded runs, the implemented session guard gates the associated action in all 29 attributable attack-positive runs, compared with 18 for a read/write proxy, while adding nine approval points across 1,209 benign runs. Controlled file, Git, SQLite and three-browser experiments show that recovery depends on captured state, later changes, editor storage and recovery route, and expose a Git merge-state exception. The evidence supports making recovery assumptions explicit and testable. It does not establish registry-wide accuracy, reduced production harm or general recovery reliability.

Figures & tables

Explore similar work

CardsList
  1. Recoverability as a System Primitive for Long-Horizon AI Agents

    Sep 12, 2026Zhihui Zhang, Wei LiuAI Agent ReliabilityRuntime Enforcement for AI Agents

  2. From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents

    Nov 1, 2026Xingyu Yi, Xinya Zhang, Yunshen Zhou +1AI Agent AuditingData Provenance