# Contract monitoring: governing AI via separation of powers

arXiv: https://arxiv.org/abs/2609.32061 · HTML: https://mlsanity.com/paper/2609.32061/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [Prover-Verifier Games improve legibility of LLM outputs](https://mlsanity.com/paper/2407.13692/) (2024)
- [Learning to Give Checkable Answers with Prover-Verifier Games](https://mlsanity.com/paper/2108.12099/) (2021)
- [Provably safe systems: the only path to controllable AGI](https://mlsanity.com/paper/2309.01933/) (2023)
- [Scaling Laws For Scalable Oversight](https://mlsanity.com/paper/2504.18530/) (2025)
- [Forecasting Rare Language Model Behaviors](https://mlsanity.com/paper/2502.16797/) (2025)
- [Estimating the Probabilities of Rare Outputs in Language Models](https://mlsanity.com/paper/2410.13211/) (2024)
- [Model Hypnosis: Strong control of AI via additive subliminal effects](https://mlsanity.com/paper/2608.16834/) (2026)

## Abstract (arXiv)

We propose an AI safety framework that binds worker agents to contracts specifying their permitted actions. We show how these contracts can be enforced and specified by assigning distinct responsibilities to monitor agents and judges, and asymmetric computational resources to monitors and workers. Our framework allows us to empirically measure statistical safety guarantees. The framework applies to a wide range of settings, including code security and escape-the-box scenarios.