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

arXiv: https://arxiv.org/abs/2609.24812 · HTML: https://mlsanity.com/paper/2609.24812/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [MiMo-Audio: Audio Language Models are Few-Shot Learners](https://mlsanity.com/paper/2512.23808/) (2025)
- [Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models](https://mlsanity.com/paper/2507.23159/) (2025)
- [Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner](https://mlsanity.com/paper/2510.07838/) (2025)
- [Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency](https://mlsanity.com/paper/2604.04847/) (2026)
- [τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains](https://mlsanity.com/paper/2603.13686/) (2026)
- [MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models](https://mlsanity.com/paper/2511.10262/) (2025)
- [Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction](https://mlsanity.com/paper/2512.14865/) (2025)
- [SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models](https://mlsanity.com/paper/2603.16859/) (2026)
- [Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge](https://mlsanity.com/paper/2604.21406/) (2026)
- [MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios](https://mlsanity.com/paper/2508.08155/) (2025)
- [Instruct-FD: Can Your Full-Duplex Speech System Follow Turn-Taking Instructions?](https://mlsanity.com/paper/2607.20460/) (2026)
- [Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue](https://mlsanity.com/paper/2603.11409/) (2026)
- [IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflows](https://mlsanity.com/paper/2606.19595/) (2026)
- [Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions](https://mlsanity.com/paper/2604.17358/) (2026)
- [Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction](https://mlsanity.com/paper/2605.17360/) (2026)

## Built on by (most cited first, 4 of 4)

- [Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes](https://mlsanity.com/paper/2609.30798/) (2026)
- [Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations](https://mlsanity.com/paper/2609.32522/) (2026)
- [Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change](https://mlsanity.com/paper/2609.35922/) (2026)
- [MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue](https://mlsanity.com/paper/2610.20172/) (2026)

## Abstract (arXiv)

Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and collaborative work, are inherently multi-speaker. Supporting these settings introduces challenges that are largely absent from one-on-one interaction. We introduce the Multi-Speaker Interaction Benchmark (MSI-Bench) for evaluating multi-speaker voice interaction. Each test case is a short multi-party multi-turn audio scene with participant context, expected tool calls, and atomic rubrics. The benchmark targets three capability families: multi-speaker memory, multi-speaker instruction following, and multi-speaker reasoning. It comprises 1,152 test cases, evenly split between Mandarin Chinese and English (576 each). The strongest configuration on each split passes all rubrics on only 66.8% of English and 54.5% of Mandarin cases, and the strongest open-weight configuration on 34.0% and 19.3%. Failure analysis separates perception from reasoning: open-weight models are bottlenecked by the multi-speaker audio front-end, while frontier systems still fail speaker-scoped decision making on clean transcripts---and models across the board often respond when no one has addressed them. These results identify speaker-grounded perception, speaker-scoped decision making, and conversational restraint as concrete targets for future voice agents.