Skip to content
Search
paperAugust 2026Unreviewed

HRGuard: Gating Relationship Manipulation in Multi-Turn Agentic AI Conversations

Pei-Sze Tan, Tasuku Igarashi, Isao Echizen

View resourcePDF

Abstract

Agentic AI assistants are increasingly used in everyday life. However, they may also be misused to support harmful manipulation in interpersonal relationships. This problem is role-sensitive. Requests from users who seek to manipulate others should be blocked. Users who seek protection from manipulation should instead receive supportive guidance. We study agentic relationship harm, which describes harm to human-human relationships that is mediated or assisted by AI agents. In multi-turn settings

Categories

Agentic Threats

Cite

@misc{tan2026hrguard,
  title = {{HRGuard: Gating Relationship Manipulation in Multi-Turn Agentic AI Conversations}},
  author = {Pei-Sze Tan and Tasuku Igarashi and Isao Echizen},
  year = {2026},
  month = aug,
  eprint = {2608.25340},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.25340}
}