VoiceAgentBench: Are Voice Assistants Ready For Agentic Tasks?

TMLR Paper7330 Authors

Abstract: Large scale Speech Language Models have enabled voice assistants capable of understanding natural spoken queries and performing complex tasks. However, existing speech benchmarks largely focus on isolated capabilities such as transcription or question answering and do not systematically evaluate agentic behavior or adversarial robustness. To address this, we introduce VoiceAgentBench, a comprehensive benchmark for evaluating SpeechLMs in realistic spoken agentic settings, comprising 6,000+ synthetic spoken queries spanning single-tool invocations, multi-tool workflows, multi-turn dialogue, and safety evaluations across English and six Indic languages. To ensure speaker diversity, we further simulate speaker variability using a novel sampling strategy that selects audios for TTS voice conversion based on speaker embeddings to maximize acoustic diversity. Our evaluation measures tool selection accuracy, structural consistency, and the correctness of tool invocations, including adversarial robustness. Across agentic tasks, ASR-LLM pipelines outperform end-to-end SpeechLMs, achieving up to 60.6\% average parameter-filling accuracy on English, while SpeechLMs exhibit lower performance and sharper degradation on Indic languages. All models struggle in sequential workflows and safety evaluations, highlighting persistent limitations in tool orchestration, multilingual generalization, and safety robustness.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Tatiana_Likhomanenko1

Submission Number: 7330