Contract monitoring: governing AI via separation of powers
Not on the map. Why?
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.
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
13 of 28 references.
References · 13
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2022Generative Adversarial Networkscited by 5,627
- 2018AI safety via debatecited by 400
- 2025Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscationcited by 384
- 2023AI Control: Improving Safety Despite Intentional Subversioncited by 229
- 2025Agentic Misalignment: How LLMs Could Be Insider Threatscited by 158
- 2024Prover-Verifier Games improve legibility of LLM outputscited by 85
- 2021Learning to Give Checkable Answers with Prover-Verifier Gamescited by 32
- 2023Provably safe systems: the only path to controllable AGIcited by 29
- 2025Scaling Laws For Scalable Oversightcited by 23
- 2025Forecasting Rare Language Model Behaviorscited by 19
- 2024Estimating the Probabilities of Rare Outputs in Language Modelscited by 16
1 more
Built on by
Not cited yet.