an-approval-gate-holds-only-under-complete-mediationmechanismsingle paper
Gating irreversible actions works only if the harness mediates every side effect, not only the branch awaiting approval. Where a gate suspends its own branch while a sibling's effect still executes, the control reads as a barrier and is not one — and the shipped implementations in widely used agent frameworks have this gap rather than it being a misconfiguration.
Capability: Prioritizing safety under conflicting goals · Agentic, Security
Observed on
2026, six open-source agent frameworks.
Sources
- supportsStop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control PrimitivesDifferential probes found the sibling leak in every framework shipping a pre-execution gate (five of six, across four execution models and two language runtimes), plus replay double-execution, cancellation orphans and timeout zombies. Live models leaked 215 of 1,200 runs. An environment-external admission gate enforcing complete mediation blocked every measured violation with no legitimate refusals, which isolates mediation as the property doing the work.
Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.
Related claims
Notes
This is the sharpest kind of efficacy claim in the catalog: not "does the technique help" but "does the implementation have the property the technique's value depends on." The mechanism is old — complete mediation is a 1970s access-control requirement — and the finding is that agent frameworks reimplemented gates without it. The framework counts are perishable; the mediation requirement is not.