# Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models

arXiv: https://arxiv.org/abs/2610.08125 · HTML: https://mlsanity.com/paper/2610.08125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 65 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM](https://mlsanity.com/paper/2411.00774/) (2024)
- [Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities](https://mlsanity.com/paper/2410.11190/) (2024)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction](https://mlsanity.com/paper/2604.27393/) (2026)
- [WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models](https://mlsanity.com/paper/2602.08971/) (2026)
- [RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies](https://mlsanity.com/paper/2506.18123/) (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)
- [SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model](https://mlsanity.com/paper/2505.15670/) (2025)
- [FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems](https://mlsanity.com/paper/2507.19040/) (2025)
- [RobotArena ∞: Scalable Robot Benchmarking via Real-to-Sim Translation](https://mlsanity.com/paper/2510.23571/) (2025)
- [Raon-Speech Technical Report](https://mlsanity.com/paper/2605.23912/) (2026)
- [DuplexWorld: Can voice agents help you get through the day?](https://mlsanity.com/paper/2608.10716/) (2026)
- [Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction](https://mlsanity.com/paper/2605.17360/) (2026)
- [M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models](https://mlsanity.com/paper/2607.29125/) (2026)
- [LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability](https://mlsanity.com/paper/2607.06157/) (2026)
- [A frontend-backend architecture for tool calls in full-duplex speech models](https://mlsanity.com/paper/2609.19334/) (2026)

## Abstract (arXiv)

Full-duplex spoken dialogue models listen and speak at the same time, enabling voice agents to have natural, low-latency interactions that turn-based systems cannot offer. However, they are commonly evaluated against single-sided interlocutors: pre-recorded audio that cannot react, or an automated examiner that reacts in real time but only administers a fixed sequence of tests and is never graded. These single-sided frameworks evaluate only half of a two-body problem, where turn-taking, overlap, and interruption are joint products of two coupled speakers. We propose DyaFDB, a framework that evaluates full-duplex models in a dyadic setup: two models converse directly under assigned roles with cooperative or conflicting goals, and both sides are scored offline with an external judge. DyaFDB probes how the two models behave toward each other, such as how they take turns or carry an assigned role under different interests. We instantiate four tasks as 140 scenarios and record 7,560 conversations, covering six self- and cross-play pairings. Throughout the experiments, we observe that how a model behaves continually reshapes its partner. We thus demonstrate that each model must be both the examiner and examinee of the other, and no single fixed interlocutor can play both parts. We will release the scenarios, role prompts, and recording protocols between two full-duplex models, without any pre-recorded audio.