AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding

• URL: http://arxiv.org/abs/2512.16250v1
• Date: Thu, 18 Dec 2025 07:01:47 GMT
• Title: AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
• Authors: Sanjoy Chowdhury, Karren D. Yang, Xudong Liu, Fartash Faghri, Pavan Kumar Anasosalu Vasu, Oncel Tuzel, Dinesh Manocha, Chun-Liang Li, Raviteja Vemulapalli,
• Abstract summary: Recent large language models (MLLMs) show strong perception but struggle in multi-speaker, dialogue-centric settings.<n>We introduce AMUSE, a benchmark designed around tasks that are inherently agentic.<n>We propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation.
• Score: 73.05946667683259
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and grounding events across time. These scenarios are central to multimodal audio-video understanding, where models must jointly reason over audio and visual streams in applications such as conversational video assistants and meeting analytics. We introduce AMUSE, a benchmark designed around tasks that are inherently agentic, requiring models to decompose complex audio-visual interactions into planning, grounding, and reflection steps. It evaluates MLLMs across three modes zero-shot, guided, and agentic and six task families, including spatio-temporal speaker grounding and multimodal dialogue summarization. Across all modes, current models exhibit weak multi-speaker reasoning and inconsistent behavior under both non-agentic and agentic evaluation. Motivated by the inherently agentic nature of these tasks and recent advances in LLM agents, we propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation as reward and selective parameter adaptation for data and parameter efficient updates. Using RAFT, we achieve up to 39.52\% relative improvement in accuracy on our benchmark. Together, AMUSE and RAFT provide a practical platform for examining agentic reasoning in multimodal models and improving their capabilities.

Related papers

• Covo-Audio Technical Report [61.09708870154148]
  Covo-Audio, a 7B-end LALM, directly processes continuous audio inputs and generates audio outputs within a single unified architecture.<n>Covo-Audio-Chat, a dialogue-oriented variant, demonstrates semantic strong spoken conversational abilities.
  arXiv  Detail & Related papers  (2026-02-10T14:31:11Z)
• Adaptive Multi-Agent Reasoning for Text-to-Video Retrieval [12.701443847087164]
  We propose an adaptive multi-agent retrieval framework that orchestrates specialized agents over multiple reasoning iterations.<n>Our framework achieves a twofold improvement over CLIP4Clip and significantly outperforms state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2025-12-02T09:52:51Z)
• MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction [52.89860691282002]
  Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce.<n>Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data.<n>We introduce textscmodelname, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences.
  arXiv  Detail & Related papers  (2025-10-07T06:27:42Z)
• ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following [0.2999888908665658]
  We introduce MMDR-Bench (Multi-Modal Dialogue Reasoning Benchmark), a novel dataset comprising 300 complex multi-turn dialogue scenarios.<n>We also propose CoLVLM Agent (Contextual LVLM Agent), a holistic framework that enhances existing LVLMs with advanced reasoning and instruction following capabilities.<n>Our experiments on MMDR-Bench demonstrate that CoLVLM Agent consistently achieves superior performance, attaining an average human evaluation score of 4.03.
  arXiv  Detail & Related papers  (2025-08-21T02:09:02Z)
• MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks [67.31276358668424]
  We introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in response to a query and link them together to generate the most informative answer.<n> AVHaystacks is an audio-visual benchmark comprising 3100 annotated QA pairs designed to assess the capabilities of LMMs in multi-video retrieval and temporal grounding task.<n>We propose a model-agnostic, multi-agent framework to address this challenge, achieving up to 89% and 65% relative improvements over baseline methods on BLEU@4 and GPT evaluation scores in QA task on our proposed AVHaystack
  arXiv  Detail & Related papers  (2025-06-08T06:34:29Z)
• Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts [56.7225771305861]
  This paper introduces Multi-Modal Retrieval-Augmented Generation (M$2$RAG), a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models.<n>The benchmark comprises four tasks: image captioning, multi-modal question answering, multi-modal fact verification, and image reranking.<n>To enhance the context utilization capabilities of MLLMs, we also introduce Multi-Modal Retrieval-Augmented Instruction Tuning (MM-RAIT)
  arXiv  Detail & Related papers  (2025-02-24T16:25:25Z)
• Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model [8.604654904400027]
  We introduce CoALM (Conversational Agentic Language Model), a unified approach that integrates both conversational and agentic capabilities.<n>Using CoALM-IT, we train three models CoALM 8B, CoALM 70B, and CoALM 405B, which outperform top domain-specific models.
  arXiv  Detail & Related papers  (2025-02-12T22:18:34Z)
• ChatterBox: Multi-round Multimodal Referring and Grounding [108.9673313949746]
  We present a new benchmark and an efficient vision-language model for this purpose. The proposed model, named ChatterBox, utilizes a two-branch architecture to collaboratively handle vision and language tasks. Experiments show that ChatterBox outperforms existing models in MRG both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2024-01-24T09:02:00Z)
• Application of frozen large-scale models to multimodal task-oriented dialogue [0.0]
  We use the existing Large Language Models ENnhanced to See Framework (LENS Framework) to test the feasibility of multimodal task-oriented dialogues. The LENS Framework has been proposed as a method to solve computer vision tasks without additional training and with fixed parameters of pre-trained models.
  arXiv  Detail & Related papers  (2023-10-02T01:42:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.