Metraipolis › archive › dc_f1bf481eca7d

When Should AI Agents Ask? Clarification Requests Under Limited Human Attention — arXiv:2610.41129

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41129
License (as archived): CC0-1.0
Archived: 2026-11-03T07:11:12.557Z
SHA-256 of the archived text: 4a9f98d3b19a05e49a25f11c2bca4656f1b59508d8dbedbda078c3d8fc02773a
Stable URL of this page: https://metraipolis.com/documento/dc_f1bf481eca7d

How to cite

When Should AI Agents Ask? Clarification Requests Under Limited Human Attention — arXiv:2610.41129 — arXiv (en), https://arxiv.org/abs/2610.41129 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1bf481eca7d (Metraipolis archive dc_f1bf481eca7d, sha256 4a9f98d3b19a05e49a25f11c2bca4656f1b59508d8dbedbda078c3d8fc02773a)

BibTeX

@misc{dcf1bf481eca7d,
  title = {When Should AI Agents Ask? Clarification Requests Under Limited Human Attention — arXiv:2610.41129},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41129},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1bf481eca7d; sha256 4a9f98d3b19a05e49a25f11c2bca4656f1b59508d8dbedbda078c3d8fc02773a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41129. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents increasingly carry out delegated tasks in parallel, with one person overseeing several of them at once. In practice, an agent often lacks information its task requires, such as an unstated preference, constraint, or specification. It can ask the human to clarify, or it can search for the information itself, for example in past records, which takes time and effort and may fail. In this paper, we study how to coordinate these decisions across several agents that share one human with limited attention. We build a stylized model in which each agent can search, ask, or continue the parts of its task that do not depend on the missing information, and we formulate the problem as a dynamic program. We first show that whether an agent should ask depends on more than its own uncertainty: an agent with other work to do can be better off asking earlier, and which question the human should answer first depends on all waiting questions, so no ranking computed agent by agent is optimal. We then propose the Pairwise Coordination Policy (PCP), which uses exact one- and two-task problems to estimate how pairs of tasks delay each other when they share the human. Theoretically, PCP is exactly optimal when at most two requirements remain unresolved and costs at most twice the optimum when every unresolved requirement must be resolved by the human. We evaluate PCP on 864 synthetic cases and in a case study with LLM agents. On the synthetic benchmark, PCP's mean gap to optimal cost is 0.07%, and it reduces cost by an average of 18-31% relative to three standard rules for when to ask. In the LLM case study, agents completed every task correctly, and PCP achieved the lowest mean cost in all tested settings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.41129 — 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 2026-11-03T07:09:31.743Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).