AMUSE: エージェント的マルチスピーカー理解のための音声視覚ベンチマークとアライメントフレームワーク

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

AuthorsSanjay Chowdhury†, Karren D. Yang, Xudong Liu, Fartash Faghri, Pavan Kumar Anasosalu Vasu, Oncel Tuzel, Dinesh Manocha†, Chun-Liang Li**, Raviteja Vemulapalli

View publication

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.

† University of Maryland, College Park

** Work done while at Apple

Related readings and updates.

AgentBuilder: Exploring Scaffolds for Prototyping User Experiences of Interface Agents

January 9, 2026research area Human-Computer Interaction

Interface agents powered by generative AI models (referred to as “agents”) can automate actions based on user commands. An important aspect of developing agents is their user experience (i.e., agent experience). There is a growing need to provide scaffolds for a broader set of individuals beyond AI engineers to prototype agent experiences, since they can contribute valuable perspectives to designing agent experiences. In this work, we explore the…

Towards Learning Multi-Agent Negotiations via Self-Play

January 28, 2019research area Computer VisionWorkshop at ICCV

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents’ intentions and possible future actions. Traditional methods formulate the problem as a Markov Decision Process, but the solutions often rely on various assumptions and become brittle when presented with corner cases. In…

Discover opportunities in Machine Learning.

Our research in machine learning breaks new ground every day.