cs.HCOct 30, 2026

When AI Agents Act on Our Behalf: A Taxonomy of Human-Agent Interaction Failure

Authors: Canwen Wang, Qing Xiao, Haiyi Zhu, Hong Shen

Organizations: Carnegie Mellon University, Pittsburgh, USA

Abstract

AI agents write and execute code, manipulate user interfaces, and transact on their users' behalf. We ask what forms failure takes in human-agent interaction, and how those forms change as agents act with greater autonomy. From 695 documented incidents in two public repositories, we developed 12 failure modes bottom-up within three interaction stages adapted from Amershi et al.'s guidelines, coding the autonomy at which each arose. What a person can do when an agent fails depends on how much the agent completes between points of user involvement--a property fixed at deployment. Therefore, the same model on the same task can fail differently under different configurations. All 12 modes appear at both low and high autonomy, and rising autonomy changes the form each failure takes. Users need controls between full delegation and full manual work, and neither incident records nor agent benchmarks reach the interaction where these failures occur.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures

    Oct 26, 2026Shravika Mittal, Sunnie S. Y. Kim, Scott Counts +3Agent Failure AnalysisAI Agent Reliability

  2. AgentRx: Diagnosing AI Agent Failures from Execution Trajectories

    Feb 2, 2026Shraddha Barke, Arnav Goyal, Alind Khare +3Fault DiagnosisAI Agent Reliability

  3. Invisible failures in human-AI interactions

    Mar 16, 2026Christopher Potts, Moritz SudhofHuman-AI Interaction