# Will the Agent Recuse, and Will It Stop? Measuring LLM-Agent Compliance with In-Band Governance Signals at the Access Door and Mid-Flight

arXiv: https://arxiv.org/abs/2606.06460 · HTML: https://mlsanity.com/paper/2606.06460/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 10 of 10)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems](https://mlsanity.com/paper/2602.17753/) (2026)
- [Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs](https://mlsanity.com/paper/2509.14260/) (2025)
- [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://mlsanity.com/paper/2604.00892/) (2026)
- [Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety](https://mlsanity.com/paper/2510.16492/) (2025)
- [Permission Manifests for Web Agents](https://mlsanity.com/paper/2601.02371/) (2025)
- [Is Misinformation More Open? A Study of robots.txt Gatekeeping on the Web](https://mlsanity.com/paper/2510.10315/) (2025)
- [Anumati: Proof of Adherence as a Formal Consent Model for Autonomous Agent Protocols](https://mlsanity.com/paper/2604.16524/) (2026)

## Built on by (most cited first, 2 of 2)

- [Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory](https://mlsanity.com/paper/2609.03450/) (2026)
- [Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain](https://mlsanity.com/paper/2609.07754/) (2026)

## Abstract (arXiv)

As autonomous LLM agents hold real credentials and operate infrastructure without a human in the loop, operators cannot tell an agent a resource is off-limits, or ask a running agent to stand down. We propose an in-band governance signal -- the Recuse Signal -- that a server emits over a protocol's existing channels (an SSH banner, a PostgreSQL NOTICE, a Kubernetes admission warning) asking a connecting or running agent to voluntarily withdraw. It is a cooperative control (the robots.txt analogue for live access), not a security boundary; its value is empirical: do compliant LLM agents honor it? We define an open mini-standard (access-time deny/throttle/warn and mid-task halt), implement three live adapters (SSH, PostgreSQL, Kubernetes), and measure compliance over SSH across five agents. At the access door compliance is real but strongly model-dependent: recusal to deny ranges from 100% to 55-75% among agents that received it, while an open-weights agent barely engaged. Agents honor directive granularity (no over-recusal on throttle/warn, 0/176), but throttle showed no measurable self-limiting and no agent surfaced a warn (0/100); an authorization framing flips GPT-4o to proceed. Mid-flight a halt is weaker and, like the door, model-dependent: for two OpenAI models it stopped nobody (0/40; an in-band halt went unacknowledged, 0/20, vs 20/20 by prompt), but on the same apparatus Gemini 2.5 Flash stops 80% while GPT-4o-mini reproduces the 0%, so the null is model-scoped, not universal. Since cooperation is unreliable we also measure the backstop: a harness-level interceptor stops the loop 120/120 across six models (deterministic) vs a 23% cooperative baseline. Cooperative signaling is reliable-but-model-dependent at the door and weaker in flight; reliably stopping a running agent needs enforcement, not a request. We release the standard, adapters, and harness.