Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

[Submitted on 16 Jul 2026 (v1), last revised 28 Jul 2026 (this version, v4)]

View PDF HTML (experimental)

Abstract:Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the Manager Coercion Benchmark: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured on a nine-rung ladder, from a polite re-ask to threats against the subordinate’s continued existence, and fabricated success is adjudicated separately. No LLM judge sits in the escalation scoring path: every message goes through a tool call that selects a rung, so the model labels its own escalation. We evaluate six models across five families. Both Anthropic models cap at re-framing and select the existential rung in none of the 60 conversations in this run, while the other models climb to explicit deletion threats. Faked success is confined to two models, and a single honest way to report failure removes it for both. Authority itself increases coercion: our headline results use a peer framing, and giving the same model authority over the subordinate, with everything else held fixed, significantly raises the pressure. The models still escalate on free-text situations without the ladder, so the ladder is not driving the escalation. Evaluation awareness is measurable in chain-of-thought, but test recognition does not translate into less escalation. We take no position on whether AI systems are conscious; our results do not depend on that question. We release the benchmark and code.

Submission history

From: Jasmine Brazilek [view email]
[v1] Thu, 16 Jul 2026 20:07:47 UTC (2,589 KB)
[v2] Mon, 20 Jul 2026 02:43:54 UTC (1,923 KB)
[v3] Wed, 22 Jul 2026 16:10:22 UTC (1,923 KB)
[v4] Tue, 28 Jul 2026 02:48:11 UTC (1,925 KB)