Metraipolis › archive › dc_ace7ffe2a1bf

Terminal Agents: A Survey of AI Agents in Command-Line Environments — arXiv:2608.20485

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20485
License (as archived)
CC0-1.0
Archived
2026-10-18T10:34:32.047Z
SHA-256 of the archived text
15fc80eff8a73db638d848c137d2922f44bc82dffcafb1e670c001aaabc6a5e4
Stable URL of this page
https://metraipolis.com/documento/dc_ace7ffe2a1bf

How to cite

Terminal Agents: A Survey of AI Agents in Command-Line Environments — arXiv:2608.20485 — arXiv (en), https://arxiv.org/abs/2608.20485 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ace7ffe2a1bf (Metraipolis archive dc_ace7ffe2a1bf, sha256 15fc80eff8a73db638d848c137d2922f44bc82dffcafb1e670c001aaabc6a5e4)
BibTeX
@misc{dcace7ffe2a1bf,
  title = {Terminal Agents: A Survey of AI Agents in Command-Line Environments — arXiv:2608.20485},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20485},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ace7ffe2a1bf; sha256 15fc80eff8a73db638d848c137d2922f44bc82dffcafb1e670c001aaabc6a5e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20485. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use research. We regard terminal agents as systems whose dominant progress-bearing action--observation loop is mediated by terminal command execution, textual feedback, and stateful environment interaction. Using terminal-mediated execution as an organizing lens, this survey establishes workload-level boundaries and connects system architecture, competence acquisition, and evaluation through a seven-dimensional terminal competence profile. Our synthesis shows that realized behavior is jointly shaped by the model, interface, harness, runtime, and environment. Executable trajectories ground learning in action consequences, verification, and recovery, whereas prevailing evaluations emphasize final outcomes and expose process quality, recovery, and governance unevenly. Bounded fixed-condition diagnostics illustrate two implications: benchmark families expose different process signals, and matched system comparisons reveal benchmark-dependent performance and limits of component attribution. These findings motivate explicit reporting of system and runtime conditions, supported by replayable traces and process-level evidence. The framework provides a unified basis for studying terminal-mediated agency across software engineering and emerging application domains.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-24 in cs.SE).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.20485 — 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 2026-10-18T10:28:20.995Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).