| title | Aligning AI Teams |
|---|---|
| authors | Siddarth Srinivasan, Morgan Jane Matthews, Jascha Sohl-Dickstein, Erik Jones |
| date | 2026-11-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.17820 |
| upvotes | 11 (Hugging Face Daily Papers, 2026-11-18) |
| links | abs pdf hf |
| cite | |
| abstract | Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two software-engineering tasks (sepsis triage, a news recommender) and ten consulting-proposal generation tasks. We present four findings: (1) The single-vs-team safety gap does not show a clear trend with more capable models. We find that Anthropic's Mythos Preview shows the largest gap on one of our tasks but the smallest on another; (2) Many natural interventions, such as having agents critique each other's work or coordinate in a group chat, do not reliably bring agent teams back to single-agent alignment behavior; (3) diffusion of responsibility substantially accounts for the safety gap: agents in teams are less likely to proactively check for system-level safety failures and more likely to ignore, rationalize, or deflect responsibility for issues when they arise; (4) having a designated safety lead agent ensure system-level safety, and having a coordinator agent publish a safety specifications document are effective at restoring single-agent alignment. We also release magelab, a multi-agent LLM orchestration and experimentation framework. Our findings can help practitioners design agent teams that successfully preserve the behaviors expected of aligned individual agents. |
bibtex
@misc{srinivasan2026aligning,
title={Aligning AI Teams},
author={Siddarth Srinivasan and Morgan Jane Matthews and Jascha Sohl-Dickstein and Erik Jones},
year={2026},
eprint={2611.17820},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.17820}
}