When AI Agents Act on Our Behalf: A Taxonomy of Human-Agent Interaction Failure
cs.HC, cs.AI, cs.CY
Submitted: 2026-10-30
Updated: 2026-10-30
Terminology
Sources
- A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- Infrastructure for AI Agents
- Agentifying Agentic AI
- Levels of Autonomy for AI Agents
- The Ethics of Advanced AI Assistants
- Multi-Agent Risks from Advanced AI
- Governing AI Agents
- Beyond Recommender: An Exploratory Study of the Effects of Different AI Roles in AI-Assisted Decision Making
- The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
- Fully Autonomous AI Agents Should Not be Developed
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems