Metraipolis › archive › dc_47a191d032a0

RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents — arXiv:2610.22507

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22507
License (as archived)
CC0-1.0
Archived
2026-10-19T08:43:24.629Z
SHA-256 of the archived text
f2de3ab865e33a9bc34fd34c2f72c3191ee0016e1bd05d5278a340cd6ff75bbb
Stable URL of this page
https://metraipolis.com/documento/dc_47a191d032a0

How to cite

RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents — arXiv:2610.22507 — arXiv (en), https://arxiv.org/abs/2610.22507 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47a191d032a0 (Metraipolis archive dc_47a191d032a0, sha256 f2de3ab865e33a9bc34fd34c2f72c3191ee0016e1bd05d5278a340cd6ff75bbb)
BibTeX
@misc{dc47a191d032a0,
  title = {RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents — arXiv:2610.22507},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22507},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47a191d032a0; sha256 f2de3ab865e33a9bc34fd34c2f72c3191ee0016e1bd05d5278a340cd6ff75bbb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22507. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or evaluate task outcomes without capturing runtime collaboration quality. In this paper, we present REALCLI, a paired benchmark that unifies the evaluation of task execution and human-agent collaboration quality on realistic CLI tasks. To comprehensively measure collaboration, REALCLI builds a five-dimensional framework, operationalized into 22 sub-dimensions and 51 interaction scenario templates. REALCLI provides two modes for paired comparison: REALCLI-EXEC supplies complete specifications upfront, whereas REALCLI-COLLAB introduces a scripted user that delivers progressive information, corrections, constraint revisions, and authorization decisions. Evaluations reveal profound capability gaps in frontier agents: the best configuration attains an average score of only 49.2%, and when evaluated by the joint collaboration score ($J_{\mathrm{collab}}$), the peak performance reaches merely 37.6%. These results show that task effectiveness diverges sharply from collaboration quality, with models consistently struggling in steerability, trust calibration, and safety boundary management. REALCLI provides a rigorous, reproducible foundation for measuring and advancing collaborative CLI agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.22507 — 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 2026-10-19T08:39:24.796Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).