# τ-Multilingual: Benchmarking Voice Agents Across Languages

arXiv: https://arxiv.org/abs/2609.35820 · HTML: https://mlsanity.com/paper/2609.35820/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [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)
- [GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2110.07679/) (2021)
- [Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond](https://mlsanity.com/paper/2408.03900/) (2024)
- [VoiceAgentBench: Are Voice Assistants ready for agentic tasks?](https://mlsanity.com/paper/2510.07978/) (2025)
- [EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents](https://mlsanity.com/paper/2605.13841/) (2026)
- [X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents](https://mlsanity.com/paper/2306.17674/) (2023)
- [MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages](https://mlsanity.com/paper/2509.26601/) (2025)
- [M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models](https://mlsanity.com/paper/2607.29125/) (2026)

## Abstract (arXiv)

English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce τ-Multilingual, extending τ-Voice to Spanish, Brazilian Portuguese, Hindi, Korean, and Mandarin with native-speaker review and evaluation of generated language and spoken output. Across 4,500 full-duplex calls and five voice configurations, Spanish, Portuguese, and Hindi remain within 3.2 task-completion points of English, but Korean and Mandarin fall by 14.7 and 8.4 points. The failure modes also vary: Korean systems miss more responses, Mandarin systems interrupt more often, and both struggle with tools and entities. Grok leads task completion but scores lowest on generation quality, motivating separate task, interaction, and generation reporting. We release language packs, validated judges, and tools for community-built multilingual voice-agent evaluation.