Metraipolis › archive › dc_b368da28a2f3

BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics — arXiv:2610.10663

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10663
License (as archived)
CC0-1.0
Archived
2026-10-09T06:23:50.528Z
SHA-256 of the archived text
1bd1fb301f2dba2028c2940e87d84e3570e658e5d40dd554857400bc78721f3e
Stable URL of this page
https://metraipolis.com/documento/dc_b368da28a2f3

How to cite

BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics — arXiv:2610.10663 — arXiv (en), https://arxiv.org/abs/2610.10663 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b368da28a2f3 (Metraipolis archive dc_b368da28a2f3, sha256 1bd1fb301f2dba2028c2940e87d84e3570e658e5d40dd554857400bc78721f3e)
BibTeX
@misc{dcb368da28a2f3,
  title = {BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics — arXiv:2610.10663},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10663},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b368da28a2f3; sha256 1bd1fb301f2dba2028c2940e87d84e3570e658e5d40dd554857400bc78721f3e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10663. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bioacoustics and ethology encompass a wide range of audio understanding tasks, many of which stand to benefit from recent advances in large audio-language models. However, progress in the field has so far been assessed on a narrow set of tasks, primarily centered on label-centric biological category recognition, such as species and call-type classification. In this work, we introduce BEANS-Next, a benchmark grounded in a taxonomy of bioacoustics tasks spanning acoustic perception, biological category recognition, scene understanding, and in-context learning. Using BEANS-Next, we show that existing models exhibit limited performance beyond the task families emphasized by existing evaluations, constraining their usefulness for broader bioacoustic applications. To support progress on this broader task space, we also introduce ROOTS, a large-scale training resource built from expanded curated real-world data and previously underused behavioral and acoustic metadata, supplemented by audio-derived information and scalable synthetic generation where labeling is insufficient. We demonstrate that training on this dataset yields substantial progress across all task groups of BEANS-Next, moving audio-language models closer to their potential as general-purpose assistants for bioacoustics and ethology. To accelerate progress in the field, we open-source our benchmark, dataset, and data pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.10663 — 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 2026-10-09T05:50:31.814Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).