Adaptive Governance Control for Near-Critical Multi-Agent Systems: State Estimation, Conditional Control and Withdrawal Tests

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

This paper proposes a governance controller combining admissible measurement, bounded intervention, and independent tests of recovery after support ends. It asks whether intervention exposure changes endogenous recovery capacity and future support demand. Version 3.0 separates assisted stability from autonomous recovery and revises measurement and withdrawal conditions. A matched-budget model experiment compares 1,600 equal-amplitude interventions per arm followed by a common 6,000-step unsupported evaluation. Tapering helps only when the modeled atrophy and mismatch-gated recovery mechanisms are both present. An earlier unequal-exposure comparison is withdrawn as an admissible prediction test. All eleven predictions remain open; deployment effectiveness and general optimality are not established.