StateM Per-Run Execution Record
In StateM, each execution maintains an isolated, mutable runtime record that is strictly decoupled from the static, reusable runbook. For every individual run, StateM tracks and persists:
- A unique run identifier
- The current active state and current state-entry identifier
- The complete transition history across states
- Execution outcomes of all lifecycle hooks and before-transfer checks
- Event timestamps
- File references to state-local evidence artifacts
Separating the mutable per-run record from the static control profile ensures that multiple concurrent runs or distinct agents can operate simultaneously under the same runbook without conflating their procedural progress.
0
1
Tags
Prep Sessions
Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Ch.3 State Persistence and Continuous Optimization - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Persistent Run State and Recoverable Execution Protocols - Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Learn After
How does StateM track state-local evidence artifacts generated during an individual execution?
In StateM, separating the mutable per-run record from the static control profile ensures that multiple concurrent runs can execute using the same runbook without conflating their procedural progress.
What specific current and historical state tracking details does StateM persist in an individual run's isolated execution record?