SOURCE-LINKED INTELLIGENCE

Recoverability as a System Primitive for Long-Horizon AI Agents

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

AI agents can be interrupted while editing files, calling tools, or carrying out multi-step tasks. Restarting repeats completed work, but continuing from unverified or outdated progress can carry earlier errors forward. A saved state is not necessarily a suitable place to resume. We introduce recoverability as a system primitive that makes reuse an explicit decision: select a supported starting point and a permitted recovery action, or withhold automatic continuation. Its behavioral contract binds that choice to supporting evidence, execution, and independent checks. A reference architecture c

Read original source ↗ Open in workspace

recordType

paper

region

Global