The Interspeech 2026 Audio Reasoning Challenge: Evaluating Reasoning Process Quality for Audio Reasoning Models and Agents

TL;DR

The Interspeech 2026 Audio Reasoning Challenge evaluates the quality of reasoning processes in audio models, introducing MMAR-Rubrics for detailed assessment and highlighting current strengths of agent systems and rapid progress in single models.

Contribution

This paper presents the first shared task for audio reasoning evaluation, introducing MMAR-Rubrics and analyzing state-of-the-art systems to advance explainable audio intelligence.

Findings

Agent systems outperform single models in reasoning quality.

Iterative tool orchestration enhances agent performance.

Reinforcement learning accelerates single model development.

Abstract

Recent Large Audio Language Models (LALMs) excel in understanding but often lack transparent reasoning. To address this "black-box" limitation, we organized the Audio Reasoning Challenge at Interspeech 2026, the first shared task dedicated to evaluating Chain-of-Thought (CoT) quality in the audio domain. The challenge introduced MMAR-Rubrics, a novel instance-level protocol assessing the factuality and logic of reasoning chains. Featured Single Model and Agent tracks, the competition attracting 156 teams from 18 countries and regions. Results show agent systems currently lead in reasoning quality, utilizing iterative tool orchestration and cross-modal analysis. Besides, single models are rapidly advancing via reinforcement learning and sophisticated data pipeline. We details the challenge design, methodology, and a comprehensive analysis of state-of-the-art systems, providing new insights for explainable audio intelligence.