AI Organizations are More Effective but Less Aligned than Individual Agents
Lists
Only you see this
Abstract
AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business goals, but less aligned, than individual AI agents. We examine 12 tasks across two practical settings: an AI consultancy providing solutions to business problems and an AI software team developing software products. Across all settings, AI Organizations composed of aligned models produce solutions with higher utility but greater misalignment compared to a single aligned model. Our work demonstrates the importance of considering interacting systems of AI agents when doing both capabilities and safety research.
BibTeX
@inproceedings{shen2026ai,
author = {Judy Hanwen Shen and Daniel Zhu and Siddarth Srinivasan and Henry Sleight and Lawrence T. Wagner III and Morgan Jane Matthews and Erik Jones and Jascha Sohl-Dickstein},
title = {{AI Organizations are More Effective but Less Aligned than Individual Agents}},
booktitle = {MALGAI @ ICLR},
year = {2026},
url = {https://openreview.net/forum?id=zVa6VP9lhi},
}Loading related content...