SOURCE-LINKED INTELLIGENCE

Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Self-improving agent workflows create an audit problem when the same controller can change both its behavior and the conditions under which that behavior is judged. We present GuardrailLoop, a simulation-based testbed that makes three operational contracts jointly testable: preservation of human-defined policy, compute accounting at every recorded execution prefix, and recovery of a specified scientific state after crashes. A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions; machine-directed evolution is restricted to a code-owned feature catalog and b

Read original source ↗ Open in workspace

recordType

paper

region

Global