PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding

Abstract: Long-form audio understanding poses significant challenges for large audio LLMs (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 \textbf{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 LLMs. 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.