Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding

The paper introduces the LongAudioQA dataset to support long‑form audio meeting understanding, addressing the scarcity of task‑specific question answering data. It proposes the GRGA model, which represents heterogeneous audio features as a multi‑dimensional graph and employs an agent‑planning approach for retrieval and answer generation. The work aims to overcome acoustic information loss and limited long‑term context memory in existing speech QA methods and Speech LLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• nlp
• benchmarks