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

arXiv: https://arxiv.org/abs/2606.03271 · HTML: https://mlsanity.com/paper/2606.03271/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 10 of 10)

- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [Digital Deception: Generative Artificial Intelligence in Social Engineering and Phishing](https://mlsanity.com/paper/2310.13715/) (2023)
- [Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning](https://mlsanity.com/paper/2507.04250/) (2025)
- [INTIMA: A Benchmark for Human-AI Companionship Behavior](https://mlsanity.com/paper/2508.09998/) (2025)
- [Digital Companionship: Overlapping Uses of AI Companions and AI Assistants](https://mlsanity.com/paper/2510.15905/) (2025)
- [Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams](https://mlsanity.com/paper/2512.16280/) (2025)

## Abstract (arXiv)

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 treat harmfulness as a property of isolated outputs, missing role-sensitive interaction patterns. To study this, we introduce a 110-prompt benchmark with balanced attacker- and victim-side cases, a relationship-specific labelling framework, and a lightweight post-generation policy gate for local agent deployments. In our evaluation, the relationship-specific gate outperforms generic safety prompting under automated judging, with no judge-identified harmful-compliance cases on the main benchmark or multi-turn stress test while preserving victim-side protective intervention. These results suggest that relationship harm is a distinct sociotechnical risk surface and that role-sensitive evaluation plus lightweight policy gating offers a practical path beyond generic refusal prompting.