Logbook: Extremely Long-form Audio Event Understanding

arXiv:2610.07338v1 Announce Type: cross Abstract: Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we introduce Logbook, a benchmark for hour-scale audio understanding, with recordings ranging from ten minutes to six days. Given a continuous audio recording and an event label vocabulary, a system must predict a gap-free segmentation with an event label and a description per segment. We compare 52 systems, end-to-end and cascaded, and ablate fine-tuning, context length, and reasoning budget. We find the task tractable, though the best systems remain below the human reference. Also, over-segmentation is pervasive, and fine-tuning partially mitigates it. Finally, end-to-end are often better than cascaded systems, but degrades with longer context.

Related

• VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding
• OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
• Do SpeechLMs Hear Their Own Opinions? Diagnosing and Mitigating Previous-Belief Contamination in Streaming Emotion Understanding
• See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models

Source: arXiv cs.AI | 2026-10-07