arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.14224cs.SDcs.CLcs.MM
收藏

Interspeech 2026音频推理挑战:评估音频推理模型和代理的推理过程质量

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

Shanghai Jiao Tong University(上海交通大学);Nanyang Technological University(南洋理工大学);Queen Mary University of London(伦敦大学Queen Mary);NVIDIA(NVIDIA公司);Carnegie Mellon University(卡内基梅隆大学);Qwen Team, Alibaba Group(通义实验室,阿里巴巴集团);Microsoft Corporation(微软公司)

Ziyang Ma, Ruiyang Xu, Yinghao Ma, Chao-Han Huck Yang, Bohan Li, Jaeyeon Kim, Jin Xu, Jinyu Li, Carlos Busso, Kai Yu, Eng Siong Chng, Xie Chen

AI总结:

Interspeech 2026音频推理挑战通过评估推理过程质量,探讨了音频推理模型和代理在事实性和逻辑性方面的表现及改进方向。

摘要:

近年来,大型音频语言模型(LALMs)在理解方面表现出色,但往往缺乏透明的推理能力。为了解决这一“黑箱”限制,我们组织了Interspeech 2026的音频推理挑战,这是首个专门评估链式思维(CoT)质量的共享任务。该挑战引入了MMAR-Rubrics,一种新的实例级协议,用于评估推理链的事实性和逻辑性。该挑战包含单模型和代理两个赛道,吸引了来自18个国家和地区的156支队伍。结果显示,代理系统目前在推理质量上占据优势,利用迭代工具编排和跨模态分析。此外,单模型通过强化学习和复杂的数据管道迅速发展。我们详细介绍了该挑战的设计、方法论以及对最先进系统的全面分析,为可解释的音频智能提供了新的见解。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑