paperJune 2026Unreviewed

Agentic Relationship Harm: Benchmarking and Gating Relational Manipulation in AI Agents

Pei-Sze Tan, Tasuku Igarashi, Isao Echizen

Abstract

AI agents built on large language models can assist not only legitimate tasks but also relational manipulation. AI agents can be used to help a user maintain a deceptive identity, intensify emotional dependency, isolate a target, or prepare for later extraction. We conceptualise this risk as agentic relationship harm: workflow-level assistance that can exploit recipient vulnerability, persuasive influence, and relational power asymmetry. Existing safety evaluations and generic guardrails often t

Cite

@misc{tan2026agentic,
  title = {{Agentic Relationship Harm: Benchmarking and Gating Relational Manipulation in AI Agents}},
  author = {Pei-Sze Tan and Tasuku Igarashi and Isao Echizen},
  year = {2026},
  month = jun,
  eprint = {2606.03271},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.03271}
}