Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes

arXiv:2609.30798 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Benchmark — 47× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Benchmarking — 6× in this paper · explained in 3 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Agentic Evaluation — 3× in this paper · explained in 1 episode
• GRPO — 3× in this paper · explained in 6 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Alignment Problem — 2× in this paper · explained in 1 episode
• Interpretability — 2× in this paper · explained in 15 episodes
• LoRA Adaptation — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Affective Computing — 1× in this paper · explained in 1 episode
• Agentic Retrieval — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Modality Gap — 1× in this paper · explained in 4 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• GAMMS: Graph based Adversarial Multiagent Modeling Simulator
• Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
• Moshi: a speech-text foundation model for real-time dialogue
• Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents
• Recent Advances in Speech Language Models: A Survey
• Direct Speech-to-Speech Neural Machine Translation: A Survey
• MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
• OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
• Simultaneous Speech-to-Speech Translation Without Aligned Data
• DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling
• Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial
• DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization
• LTS-VoiceAgent: A Listen-Think-Speak Framework for Efficient Streaming Voice Interaction via Semantic Triggering and Incremental Reasoning
• Voice Activity Projection: Self-supervised Learning of Turn-taking Events
• How Much Does Prosody Help Turn-taking? Investigations using Voice Activity Projection Models
• Multilingual Turn-taking Prediction Using Voice Activity Projection
• Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection
• Voice Activity Projection Model with Multimodal Encoders
• Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems
• MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection