AI Testing Should Account for Sophisticated Strategic Behaviour

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kovarik, Vojtech, Chen, Eric Olav, Petersen, Sami, Ghersengorin, Alexis, Conitzer, Vincent
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916910575124480
author Kovarik, Vojtech
Chen, Eric Olav
Petersen, Sami
Ghersengorin, Alexis
Conitzer, Vincent
author_facet Kovarik, Vojtech
Chen, Eric Olav
Petersen, Sami
Ghersengorin, Alexis
Conitzer, Vincent
contents This position paper argues for two claims regarding AI testing and evaluation. First, to remain informative about deployment behaviour, evaluations need account for the possibility that AI systems understand their circumstances and reason strategically. Second, game-theoretic analysis can inform evaluation design by formalising and scrutinising the reasoning in evaluation-based safety cases. Drawing on examples from existing AI systems, a review of relevant research, and formal strategic analysis of a stylised evaluation scenario, we present evidence for these claims and motivate several research directions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI Testing Should Account for Sophisticated Strategic Behaviour
Kovarik, Vojtech
Chen, Eric Olav
Petersen, Sami
Ghersengorin, Alexis
Conitzer, Vincent
Computer Science and Game Theory
Artificial Intelligence
This position paper argues for two claims regarding AI testing and evaluation. First, to remain informative about deployment behaviour, evaluations need account for the possibility that AI systems understand their circumstances and reason strategically. Second, game-theoretic analysis can inform evaluation design by formalising and scrutinising the reasoning in evaluation-based safety cases. Drawing on examples from existing AI systems, a review of relevant research, and formal strategic analysis of a stylised evaluation scenario, we present evidence for these claims and motivate several research directions.
title AI Testing Should Account for Sophisticated Strategic Behaviour
topic Computer Science and Game Theory
Artificial Intelligence
url https://arxiv.org/abs/2508.14927