Metraipolis › archive › dc_d52fec464ebd

What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents — arXiv:2608.03099

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03099
License (as archived): CC0-1.0
Archived: 2026-10-31T12:30:57.334Z
SHA-256 of the archived text: ae2571f5c9d67d3f2811af41fd2ab38f1a94b53ee80665be744b22e1e2039ed0
Stable URL of this page: https://metraipolis.com/documento/dc_d52fec464ebd

How to cite

What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents — arXiv:2608.03099 — arXiv (en), https://arxiv.org/abs/2608.03099 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d52fec464ebd (Metraipolis archive dc_d52fec464ebd, sha256 ae2571f5c9d67d3f2811af41fd2ab38f1a94b53ee80665be744b22e1e2039ed0)

BibTeX

@misc{dcd52fec464ebd,
  title = {What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents — arXiv:2608.03099},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03099},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d52fec464ebd; sha256 ae2571f5c9d67d3f2811af41fd2ab38f1a94b53ee80665be744b22e1e2039ed0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03099. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foundation models place language throughout embodied agents, but its presence does not show what it contributes or how well that contribution is grounded. This survey separates these two questions. We define five non-exclusive functional roles for language: Specification, Embodied Representation, Action Orchestration, Grounding Regulation, and Execution Coupling. For each role, we trace the path from linguistic content to its embodied consumer and identify the observations or interventions that can test the claimed responsibility. Applying this framework to the reviewed literature reveals a recurring gap between functional use and evidential support. Interpretable or revised linguistic intermediates may be incorrect, go unused, or fail to affect later behavior. Even when actions are directly conditioned on language, system-level success does not by itself isolate language's contribution. We therefore evaluate grounding claim by claim, asking whether the reported evidence supports the specific responsibility assigned to language. Using role claims rather than architectures as the unit of comparison allows us to compare modular and end-to-end embodied agents without extending conclusions beyond the reported evidence.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.03099 — 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 2026-10-31T12:17:37.742Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).