# Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives

arXiv: https://arxiv.org/abs/2607.14166 · HTML: https://mlsanity.com/paper/2607.14166/

## Key facts

- Cited by 3 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 15 of its 94 references that are in the map.
- First posted on arXiv 15 Jul 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, 15 of 15)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems](https://mlsanity.com/paper/2403.04960/) (2024)
- [AIOS: LLM Agent Operating System](https://mlsanity.com/paper/2403.16971/) (2024)
- [SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning](https://mlsanity.com/paper/2503.11951/) (2025)
- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems](https://mlsanity.com/paper/2606.17182/) (2026)
- [Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents](https://mlsanity.com/paper/2603.00476/) (2026)

## Built on by (most cited first, 3 of 3)

- [Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers](https://mlsanity.com/paper/2608.03836/) (2026)
- [Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution](https://mlsanity.com/paper/2609.21284/) (2026)
- [Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback](https://mlsanity.com/paper/2610.00347/) (2026)

## Abstract (arXiv)

Production LLM-agent frameworks ship control primitives -- human-in-the-loop approval gates, run cancellation, and execution timeouts -- whose names and documentation imply barrier semantics: while a run is paused, cancelled, or timed out, no gated side effect executes. This contract holds on none of six widely used open-source frameworks. Model-free differential probes isolate a recurring sibling leak -- an approval gate suspends its own branch while a sibling's effect executes during the pause, defeating rejection -- in every framework shipping a pre-execution gate (five of six, four execution models, two language runtimes), and confirm replay double-execution, cancellation orphans, and timeout zombies. The hazard is reachable: frontier models emit the leak-triggering plan shape at rates up to 14%, and live models driving unmodified frameworks leak 215 of 1,200 runs (P(leak | emitted)=1.00); on naturalistic tau-bench episodes models serialize writes -- the everyday gap is latent -- while injection induces it deterministically and a 13-incident public corpus corroborates the replay and cancellation failures. We repair the gaps with SOUNDGATE, an environment-external Rust gate through which every side effect must be admitted, enforcing hold-until-decided, reject-cancels, dedup-on-replay, and fence-on-cancel under a stated complete-mediation contract, discharged for network egress by two kernel-enforced routes. The admission core is mechanically verified (Verus; TLA+/TLC to 7.5e7 states; TLAPS; Loom on the deployed Rust) and bridged to code by differential conformance over 1.2e7 operations with zero divergences. Under that contract SOUNDGATE blocks every measured violation on all six frameworks while releasing legitimate effects: gated tau-bench episodes complete with zero refusals at ~1 ms per write, and durable admission sustains ~12k admissions per second.