From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911639470604288 |
|---|---|
| author | Xu, Ke Wang, Yuhao Wang, Yu |
| author_facet | Xu, Ke Wang, Yuhao Wang, Yu |
| contents | Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus on reactive responses, overlooking the complexities of proactive intervention and monitoring. To bridge this gap, we introduce ProVoice-Bench, the first evaluation framework specifically designed for proactive voice agents, featuring four novel tasks. By leveraging a multi-stage data synthesis pipeline, we curate 1,182 high-quality samples for rigorous testing. Our evaluation of state-of-the-art Multimodal LLMs reveals a significant performance gap, particularly regarding over-triggering and reasoning capabilities. These findings highlight the limitations of current models and offer a roadmap for developing more natural, context-aware proactive agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15037 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench Xu, Ke Wang, Yuhao Wang, Yu Artificial Intelligence Computation and Language Sound Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus on reactive responses, overlooking the complexities of proactive intervention and monitoring. To bridge this gap, we introduce ProVoice-Bench, the first evaluation framework specifically designed for proactive voice agents, featuring four novel tasks. By leveraging a multi-stage data synthesis pipeline, we curate 1,182 high-quality samples for rigorous testing. Our evaluation of state-of-the-art Multimodal LLMs reveals a significant performance gap, particularly regarding over-triggering and reasoning capabilities. These findings highlight the limitations of current models and offer a roadmap for developing more natural, context-aware proactive agents. |
| title | From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench |
| topic | Artificial Intelligence Computation and Language Sound |
| url | https://arxiv.org/abs/2604.15037 |