Metraipolis › archive › dc_bc90de824994

APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction — arXiv:2609.34973

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34973
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:24.619Z
SHA-256 of the archived text
09c1908a064dc5348cef69a13ebeead68bb8093db87d9065ca46927a149ab406
Stable URL of this page
https://metraipolis.com/documento/dc_bc90de824994

How to cite

APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction — arXiv:2609.34973 — arXiv (en), https://arxiv.org/abs/2609.34973 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc90de824994 (Metraipolis archive dc_bc90de824994, sha256 09c1908a064dc5348cef69a13ebeead68bb8093db87d9065ca46927a149ab406)
BibTeX
@misc{dcbc90de824994,
  title = {APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction — arXiv:2609.34973},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34973},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc90de824994; sha256 09c1908a064dc5348cef69a13ebeead68bb8093db87d9065ca46927a149ab406},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34973. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Full-duplex voice agents can now listen, speak, use tools, and act during spoken interactions, but fluent dialogue does not guarantee correct completion of delegated professional workflows. We introduce APEX-Voice, a benchmark of 120 interactive professional workflows spanning ten work archetypes such as form completion, corporate negotiation, coordination, consulting, and interviewing. Each workflow executes in a stateful Voice Workbench environment with task-specific knowledge, typed tools, gold-annotated final work artifact, authorization constraints, and a user simulation policy backed by validated, pre-compiled speech realizations. We evaluate both artifact field accuracy and end-to-end workflow success, which requires the correct terminal state, valid process, completed actions, and a valid final artifact. Across five frontier real-time voice agents-GPT-Live-1, Gemini-3.8-Live, Grok-Voice-Think-2.0, Step-Audio3, and GPT-realtime-2.1, none exceeds 25% Pass@1, and the best Reliable@3 is only 10.8%. Moreover, stateful coordination is the dominant failure point across systems, while success decreases further on workflows requiring greater knowledge retrieval and mid-speech corrections. Overall, APEX-Voice is the first benchmark for evaluating whether voice agents can translate conversational competence into dependable professional work.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34973 — 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 2026-10-07T20:29:01.742Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).