# Rational Adversaries and the Maintenance of Fragility: A Game-Theoretic Theory of Rational Stagnation

arXiv: https://arxiv.org/abs/2510.22232 · HTML: https://mlsanity.com/paper/2510.22232/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 22 references that are in the map.
- First posted on arXiv 25 Oct 2025.

## Builds on (most cited first, 1 of 1)

- [Stackelberg vs. Nash in Security Games: An Extended Investigation of Interchangeability, Equivalence, and Uniqueness](https://mlsanity.com/paper/1401.3888/) (2014)

## Built on by (most cited first, 1 of 1)

- [Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM Alignment](https://mlsanity.com/paper/2604.05965/) (2026)

## Abstract (arXiv)

Cooperative systems often remain in persistently suboptimal yet stable states. This paper explains such "rational stagnation" as an equilibrium sustained by a rational adversary whose utility follows the principle of potential loss, uD = Uideal - Uactual. Starting from the Prisoner's Dilemma, we show that the transformation ui' = a,ui + b,uj and the ratio of mutual recognition w = b/a generate a fragile cooperation band [wmin,,wmax] where both (C,C) and (D,D) are equilibria. Extending to a dynamic model with stochastic cooperative payoffs Rt and intervention costs (Cc,,Cm), a Bellman-style analysis yields three strategic regimes: immediate destruction, rational stagnation, and intervention abandonment. The appendix further generalizes the utility to a reference-dependent nonlinear form and proves its stability under reference shifts, ensuring robustness of the framework. Applications to social-media algorithms and political trust illustrate how adversarial rationality can deliberately preserve fragility.