@inproceedings{someki-etal-2026-planrag,
    title = "{P}lan{RAG}-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding",
    author = "Someki, Masao  and
      Huang, Chien-yu  and
      Arora, Siddhant  and
      Cornell, Samuele  and
      M{\textbackslash}{''}uller, Markus  and
      Susanj, Nathan  and
      Swaminathan, Rupak Vignesh  and
      Strimel, Grant  and
      Liu, Jing  and
      Watanabe, Shinji",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1304/",
    pages = "26167--26183",
    ISBN = "979-8-89176-395-1",
    abstract = "Long-form audio understanding poses significant challenges for large audio language models (LALMs) due to the extreme length of audio sequences and the need to reason over heterogeneous acoustic cues distributed over time, such as speech content, speaker identity, emotion, and sound events. To address these challenges, we propose PlanRAG-Audio, a planning-based retrieval-augmented generation framework for scalable long-form audio understanding. Rather than having audio LALMs process entire recordings directly, PlanRAG-Audio explicitly plans which modalities and temporal spans are required for a given query, and retrieves only query-relevant information from a structured text and audio database. This retrieval planning enables effective reasoning over complex, cross-domain audio queries while substantially reducing the input length passed to the large language models. Experiments across a wide range of speech/audio retrieval demonstrate that PlanRAG-Audio improves reasoning accuracy and stabilizes performance as audio duration increases by decoupling inference cost from raw audio length."
}