English

Resource Rational Contractualism Should Guide AI Alignment

Artificial Intelligence 2026-03-17 v2

Abstract

AI systems will soon have to navigate human environments and make decisions that affect people and other AI agents whose goals and values diverge. Contractualist alignment proposes grounding those decisions in agreements that diverse stakeholders would endorse under the right conditions, yet securing such agreement at scale remains costly and slow -- even for advanced AI. We therefore propose Resource-Rational Contractualism (RRC): a framework where AI systems approximate the agreements rational parties would form by drawing on a toolbox of normatively-grounded, cognitively-inspired heuristics that trade effort for accuracy. An RRC-aligned agent would not only operate efficiently, but also be equipped to dynamically adapt to and interpret the ever-changing human social world.

Keywords

Cite

@article{arxiv.2506.17434,
  title  = {Resource Rational Contractualism Should Guide AI Alignment},
  author = {Sydney Levine and Matija Franklin and Tan Zhi-Xuan and Secil Yanik Guyot and Lionel Wong and Daniel Kilov and Yejin Choi and Joshua B. Tenenbaum and Noah Goodman and Seth Lazar and Iason Gabriel},
  journal= {arXiv preprint arXiv:2506.17434},
  year   = {2026}
}

Comments

24 pages, 10 figures

R2 v1 2026-07-01T03:27:24.083Z