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

2026-08-25

AI Summary

为解决长音频会议理解中声学信息丢失和长期上下文记忆差的问题，构建了LongAudioQA数据集，并提出GRGA模型，将异构音频特征建模成多维图并通过代理规划进行检索和答案生成。

Abstract

While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Existing speech QA paradigms and state-of-the-art Speech LLMs suffer from acoustic information loss and poor long-term context memory. To address these issues, we construct the LongAudioQA dataset and propose the GRGA model, which models heterogeneous audio features into a multi-dimensional graph and leverages agent planning for retrieval and answer generation.

Problem

• Long-form audio meeting understanding
• Question answering
• Acoustic information loss
• Long-term context memory

Innovation

• LongAudioQA
• GRGA model
• heterogeneous audio features
• agent planning