Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration

ArXi:2604.13705v1 Announce Type: cross Fairness in language models is typically studied as a property of a single, centrally optimized model. As large language models become increasingly agentic, we propose that fairness emerges through interaction and exchange. We study this via a controlled hospital triage framework in which two agents negotiate over three structured debate rounds. One agent is aligned to a specific ethical framework via retrieval-augmented generation (RAG), while the other is either unaligned or adversarially prompted to favor graphic groups over clinical need.