Metraipolis › archive › dc_c167666996dc

When AI Agents Act on Our Behalf: A Taxonomy of Human-Agent Interaction Failure — arXiv:2611.00291

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00291
License (as archived)
CC0-1.0
Archived
2026-11-03T18:15:59.933Z
SHA-256 of the archived text
3c75802e24f0865966f42649cfc5fa50d2b502820eaafa317da45693947f5151
Stable URL of this page
https://metraipolis.com/documento/dc_c167666996dc

How to cite

When AI Agents Act on Our Behalf: A Taxonomy of Human-Agent Interaction Failure — arXiv:2611.00291 — arXiv (en), https://arxiv.org/abs/2611.00291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c167666996dc (Metraipolis archive dc_c167666996dc, sha256 3c75802e24f0865966f42649cfc5fa50d2b502820eaafa317da45693947f5151)
BibTeX
@misc{dcc167666996dc,
  title = {When AI Agents Act on Our Behalf: A Taxonomy of Human-Agent Interaction Failure — arXiv:2611.00291},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00291},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c167666996dc; sha256 3c75802e24f0865966f42649cfc5fa50d2b502820eaafa317da45693947f5151},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2611.00291 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:09:53.498Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).