Metraipolis › archive › dc_86e594be0ff0

Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering — arXiv:2610.20085

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20085
License (as archived)
CC0-1.0
Archived
2026-10-15T15:03:50.020Z
SHA-256 of the archived text
5efa038470475c28160212ba7f388d3592a8092b40909ec7146884a9932ce9c8
Stable URL of this page
https://metraipolis.com/documento/dc_86e594be0ff0

How to cite

Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering — arXiv:2610.20085 — arXiv (en), https://arxiv.org/abs/2610.20085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86e594be0ff0 (Metraipolis archive dc_86e594be0ff0, sha256 5efa038470475c28160212ba7f388d3592a8092b40909ec7146884a9932ce9c8)
BibTeX
@misc{dc86e594be0ff0,
  title = {Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering — arXiv:2610.20085},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20085},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86e594be0ff0; sha256 5efa038470475c28160212ba7f388d3592a8092b40909ec7146884a9932ce9c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understanding systems requires suitable textual interfaces through which multimodal reasoning can be exposed to text-based optimizers. We investigate how the design of textual interfaces affects prompt optimization for multimodal reasoning, on the audio-visual question answering task. We compare three interface designs, including a direct inference system consisting of a single omni-modal large language model (OmniLLM), a captioner-reasoner system, and an agentic architecture in which a primary agent orchestrates subagent OmniLLMs. Experiments with Qwen3-Omni and Gemini show that direct prompt optimization provides model-dependent gains; the captioner-reasoner system and the agentic system expose more interpretable optimization interfaces but are harder to optimize, where error analysis of cases affected by optimization is conducted. Our study highlights textual interface design as an important factor in making prompt optimization effective for omni-modal reasoning systems. Our implementation details are specified in GitHub repo.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, 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/2610.20085 — 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 2026-10-15T14:07:38.585Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).