Metraipolis › archive › dc_054173cd6ea3

Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation — arXiv:2610.38960

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38960
License (as archived)
CC0-1.0
Archived
2026-10-31T06:09:07.021Z
SHA-256 of the archived text
6a2c4aa30ac0ac89232b27a6b2013677bc7de1cb637941fcb0132e6e916fcd47
Stable URL of this page
https://metraipolis.com/documento/dc_054173cd6ea3

How to cite

Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation — arXiv:2610.38960 — arXiv (en), https://arxiv.org/abs/2610.38960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_054173cd6ea3 (Metraipolis archive dc_054173cd6ea3, sha256 6a2c4aa30ac0ac89232b27a6b2013677bc7de1cb637941fcb0132e6e916fcd47)
BibTeX
@misc{dc054173cd6ea3,
  title = {Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation — arXiv:2610.38960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_054173cd6ea3; sha256 6a2c4aa30ac0ac89232b27a6b2013677bc7de1cb637941fcb0132e6e916fcd47},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed evidence. Omni-modal agents, which autonomously orchestrate perception tools to actively collect evidence, achieve strong performance, but it remains unclear whether active perception from both audio and visual modalities depends on broad specialized toolsets, especially audio or visual modality-specific tools. Such systems may also introduce long execution trajectories and substantial inference cost. We investigate whether comparable performance can be retained with a compact workflow exposing only essential perceptual capabilities. Starting from the specialized-tool OmniAgent, we conduct staged controlled experiments that prune the toolset and progressively consolidate modality-specific tools into omni-modal tools, motivating a two-tool agent comprising only Omni-modal captioning and Omni-modal QA. Across three widely used AVQA benchmarks, our compact agent achieves comparable or better accuracy than the specialized-tool agent while reducing inference cost by around 70%.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.38960 — 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 2026-10-31T06:07:08.498Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).