Story
arxiv_cs_ai · Nov 13, 2026 · paper
Source brief
Aligning AI Teams
arxiv.orgNov 13, 2026
original source linked
In brief
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 sof