Lune

ACL Findings2026

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

Masao Someki, Chien-Yu Huang, Siddhant Arora, Samuele Cornell, Markus Müller, Nathan Susanj, Rupak Vignesh Swaminathan, Grant P. Strimel, Jing Liu, Shinji Watanabe

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback cites Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
  • RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
  3. WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on WikipediaSina J. Semnani, Violet Z. Yao, Heidi C. Zhang, Monica S. LamEMNLP Findings 2023 · 44 citations
  4. SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex ConversationWenyi Yu, Siyin Wang, Xiaoyu Yang, Xianzhao Chen et al.NeurIPS 2025 · 43 citations
  5. RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-FeedbackYanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu et al.ACL Findings 2024 · 35 citations

Related papers

  1. WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue ModelsYifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang et al.ACL 2025
  2. ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid ReasoningZongsheng Cao, Anran Liu, Yangfan He, Jing Li et al.AAAI 2026 · 1 citation
  3. Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting UnderstandingQuanwei Tang, Dong Zhang, Shoushan Li, Guodong ZhouACL Findings 2026
  4. LSAR: Sparse Lexical Representation Learning for Efficient and Interpretable Audio RetrievalHaoyue Li, Yuzhe Bai, Li NiuKDD 2026
  5. Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video UnderstandingXiaoqian Shen, Wenxuan Zhang, Jun Chen, Mohamed ElhoseinyNeurIPS 2025 · 37 citations
Dusk over the sea between two cliffs drawn in fine vertical lines