ChronosAudio
ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
Kaiwen Luo, Liang Lin, Yibo Zhang, Moayad Aloqaily, Jialiang Tao, Dexian Wang, et al. · 2026-05-27
- Modality
- Audio & speech
- Data
- Hybrid (real + synthetic/simulated)
- Task · ground truth
- QA/Class. · Ans.
- Scope
- Broader evaluation with memory demands
What it tests
- CECross-modal evidencePartially evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesNot evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionNot evaluated
- SPSpeaker trackingPartially evaluated
- ACAcoustic-cue retentionDirectly evaluated
- RPRepair persistenceNot evaluated
Survey notes
Audio tasks test transcription, localization, comprehension and summarization across input lengths. They do not specifically evaluate agent-memory retention or later reuse.