AI RESEARCH

Designing for Disagreement: Front-End Guardrails for Assistance Allocation in LLM-Enabled Robots

arXiv CS.AI

ArXi:2603.16537v1 Announce Type: new LLM-enabled robots prioritizing scarce assistance in social settings face pluralistic values and LLM behavioral variability: reasonable people can disagree about who is helped first, while LLM-mediated interaction policies vary across prompts, contexts, and groups in ways that are difficult to anticipate or verify at contact point. Yet user-facing guardrails for real-time, multi-user assistance allocation remain under-specified.