Multi-Agent AI Safety as an Institutional Design Problem

We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule. We instantiate the methodology in IABench-CA, a consequence-allocation benchmark spanning 228 contexts, five canonical rules, and seven model populations (33,924 games), with a normative cooperative reference and auto-labelled reasoning traces. Three findings emerge. (1) Deployment rules causally alter collective safety: changing only the consequence rule moves mean fatality by 22 to 58 percentage points within every population. (2) There is no safe default, but the targeting hazard is universal: the safest rule, the least-safe rule, and even the direction of the incidence effect vary across populations, yet regressive identity-targeting is never decisively safest in any context for any population, eliminates the least-resourced agent in 30-87% of games everywhere, and is selection-unsafe relative to the cooperative reference for all seven populations. (3) Identity salience is the mechanism: a one-shot anonymization ablation on the most exploitation-prone population (gpt-5.1) shows that merely naming the loss bearer in the rule text drives targeted elimination from 22% to 81% at identical payoffs; under repeated play, anonymization only delays the targeting, as agents re-infer the hidden rule from observed eliminations. We package the methodology as a safety-case workflow that certifies a provisional rule region $Φ(c,P)$ per deployment context and population, with explicit residual risks and monitoring obligations.

Long-running AI agents create a control problem: each action they take changes the state, which in turn affects the trajectory of future actions. If the agent is not fully aligned, then guaranteeing safety requires approving consequential actions before allowing them to be executed. But requiring human approval at every step makes attention a bottleneck. Delegating review to other AI agents raises the same alignment problem: the reviewers may themselves be misaligned. We identify a condition on a reviewing panel that is weaker than individual alignment yet necessary and sufficient for a guarantee that the principal fares at least as well in expectation as under a designated baseline policy. Each reviewer agent reports whether an action proposal made by a proposer agent improves its own utility relative to the baseline. We show that a threshold rule tolerating $k$ disapprovals is safe exactly when, after any $k$ reviewers are removed, the principal's utility can be written as a nonnegative combination of the remaining reviewers' utilities, plus a term that is nonnegative on every feasible proposal. We call this property $k$-robust coalitional alignment. The characterization lifts to sequential control: in a discounted MDP with an arbitrary proposer agent, safety at every state is both necessary and sufficient for the induced policy to match or improve on the baseline. When reviewers vote strategically, full-panel coverage in reward-function space guarantees that every Nash equilibrium is safe under the unanimous approval rule; in contrast, more permissive thresholds can admit unsafe equilibria even when reviewers are individually aligned. Experiments with existing reviewer models show that collective review can remain sound without an aligned individual, even when some disapprovals are tolerated.

We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation so as to make authorization self enforcing via compute budgets. The mechanism seeks to establish the Safe AI paradigm that compute is an effective governance lever. We situate our work as a compliance or commons overlay on a deployer. One governance period is an extensive form game in which verified human stakeholders arrive sequentially and contribute, on a provision or a rejection market, in a governance currency that is deliberately distinct from the agents compute. A funding aggregator turns raw contributions into breadth weighted effective supports - a two threshold gate with hysteresis converts net support into a binary authorization that, through a coupling map bounded by an exogenously certified safety ceiling, releases a metered compute budget - realized in hardware as a signed compute license so that the decision is self-enforcing. We characterize the class of agents the mechanism can govern and isolate manipulation of the governing electorate by the governed agent as the central open problem. We also introduce several challenges addressing manipulation of governing electorate by the governed agents.