# How reverse game theory could keep AI agents in check

> Original title: How “reverse game theory” could keep AI agents in check

- Source: MIT Technology Review · AI
- Published: 2026-11-03T10:43:41.000Z
- Bad Influence: https://badinfluence.news/items/ztyfcygdy9zhqenpaxq0a9ghl
- Original: https://www.technologyreview.com/2026/11/03/1147934/reverse-game-theory-mechanism-design-ai-alignment/

## Summary

Alignment researchers are exploring reverse game theory, also called mechanism design, to shape AI behavior through incentives rather than by inspecting a model's internal reasoning. Morris and colleagues propose rewarding models for predicting other models' answers and pitting agents against each other, while Hazan proposes solver and auditor roles. The article notes that the approach assumes rational agents and that its effectiveness in real frontier models remains unclear.