# SteerablePlex: Can We Steer Full-Duplex Models?

arXiv: https://arxiv.org/abs/2610.12201 · HTML: https://mlsanity.com/paper/2610.12201/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 38 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 7 of 7)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models](https://mlsanity.com/paper/2606.11167/) (2026)
- [Raon-Speech Technical Report](https://mlsanity.com/paper/2605.23912/) (2026)
- [Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2601.19063/) (2026)
- [Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning](https://mlsanity.com/paper/2607.07148/) (2026)

## Abstract (arXiv)

Full-duplex speech models can listen and speak simultaneously, enabling natural interaction, but become increasingly difficult to control as the conversation history grows. When used as user simulators, this lack of control can cause them to deviate from prescribed scenarios and produce unreliable evaluation outcomes. We introduce SimIF-Bench (Simulator Instruction-Following Benchmark), which evaluates whether a conversational model stays within a prescribed scenario and completes multiple goals in the required order. The benchmark reveals that current open-source full-duplex models struggle to follow such constraints. We then introduce a Group Reward-Decoupled Normalization Policy Optimization (GDPO)-based training recipe that enables a full-duplex model to follow textual instructions during an ongoing conversation while maintaining its turn-taking ability. By connecting the resulting SteerablePlex to an asynchronous backend language model that monitors the conversation and provides instructions when needed, we build a more controllable full-duplex user simulator that follows multi-stage constraints more reliably than existing open-source models and GPT-Realtime.