2025/11/06 by Claire Yang, Yang, Claire, Zhang, Claire Jie +4
Computer Science · Psychology · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multiagent Systems (cs.MA) #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #Social Robot Interaction and HRI
paper · pdf · doi:10.48550/arxiv.2511.04177
openalex publication_date 2025/11/06 · openalex created_date 2025/11/08 · openalex updated_date 2026/07/28
Personal AI agents are increasingly deployed in shared environments, where their actions affect not just the primary user they are assisting, but bystanders who never consented to being affected by the system. We show that a well-meaning AI assistant optimizing for one user's benefit can unintentionally erode a bystander's agency, a phenomenon we formalize as bystander disempowerment. We theoretically characterize the conditions under which disempowerment arises, showing it emerges when an assistant systematically selects actions that increase user empowerment at the bystander's expense. We empirically demonstrate this in Disempower-Grid, a parameterized suite of multi-agent gridworld environments, finding that between 27-96% of procedurally generated environments exhibit disempowerment, and that the presence of disempowerment depends strongly on assistant objective and capability, not just environmental structure.