Saved in:
Bibliographic Details
Main Authors: Levine, Sydney, Franklin, Matija, Zhi-Xuan, Tan, Guyot, Secil Yanik, Wong, Lionel, Kilov, Daniel, Choi, Yejin, Tenenbaum, Joshua B., Goodman, Noah, Lazar, Seth, Gabriel, Iason
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.17434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910052158275584
author Levine, Sydney
Franklin, Matija
Zhi-Xuan, Tan
Guyot, Secil Yanik
Wong, Lionel
Kilov, Daniel
Choi, Yejin
Tenenbaum, Joshua B.
Goodman, Noah
Lazar, Seth
Gabriel, Iason
author_facet Levine, Sydney
Franklin, Matija
Zhi-Xuan, Tan
Guyot, Secil Yanik
Wong, Lionel
Kilov, Daniel
Choi, Yejin
Tenenbaum, Joshua B.
Goodman, Noah
Lazar, Seth
Gabriel, Iason
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17434
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Resource Rational Contractualism Should Guide AI Alignment
Levine, Sydney
Franklin, Matija
Zhi-Xuan, Tan
Guyot, Secil Yanik
Wong, Lionel
Kilov, Daniel
Choi, Yejin
Tenenbaum, Joshua B.
Goodman, Noah
Lazar, Seth
Gabriel, Iason
Artificial Intelligence
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.
title Resource Rational Contractualism Should Guide AI Alignment
topic Artificial Intelligence
url https://arxiv.org/abs/2506.17434