MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents

arXiv:2609.24812 · cs.CL · Submitted 2026-09-21 · Read on arXiv

cs.CL

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: 23 pages, 6 figures, 5 tables. Dataset: https://huggingface.co/datasets/M2cha4l1124/MSI-Bench ; Code: https://github.com/boson-ai/MSI-Bench

Code: https://github.com/boson-ai/MSI-Bench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 21× in this paper · explained in 2 episodes
• Core — 10× in this paper · explained in 2 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• LLM judge — 2× in this paper · explained in 2 episodes
• All-Pass Rate — 1× in this paper
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Atomic Rubric Score — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Full-duplex interaction — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue
• EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
• Qwen2-Audio Technical Report
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Moshi: a speech-text foundation model for real-time dialogue
• Gemma 4 Technical Report
• Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction
• Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction
• M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models
• Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions
• Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
• Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner
• Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models
• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
• WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
• Qwen3-Omni Technical Report
• $\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
• IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflows
• Qwen3-ASR Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering