From homeostasis to resource sharing: Biologically and economically aligned multi-objective multi-agent gridworld-based AI safety benchmarks

TL;DR

This paper introduces new multi-objective, multi-agent AI safety benchmarks inspired by biological and economic principles, emphasizing homeostasis, resource sharing, and sustainability to better evaluate aligned agentic AI systems.

Contribution

It presents eight novel benchmark environments incorporating biological and economic themes to test AI safety, addressing gaps in existing benchmarks.

Findings

Identifies pitfalls like unbounded optimization and resource depletion.

Highlights challenges in balancing multiple objectives.

Demonstrates importance of safety constraints and sustainability.

Abstract

Developing safe, aligned agentic AI systems requires comprehensive empirical testing, yet many existing benchmarks neglect crucial themes aligned with biology and economics, both time-tested fundamental sciences describing our needs and preferences. To address this gap, the present work focuses on introducing biologically and economically motivated themes that have been neglected in current mainstream discussions on AI safety - namely a set of multi-objective, multi-agent alignment benchmarks that emphasize homeostasis for bounded and biological objectives, diminishing returns for unbounded, instrumental, and business objectives, sustainability principle, and resource sharing. Eight main benchmark environments have been implemented on the above themes, to illustrate key pitfalls and challenges in agentic AI-s, such as unboundedly maximizing a homeostatic objective, over-optimizing one objective at the expense of others, neglecting safety constraints, or depleting shared resources.