What Matters in Preference Post-Training of Continuous Autoregressive Speech Language Models

End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current open-source spoken dialogue models often remain below expectations. Motivated by the success of online reinforcement learning(RL) in other domains, one might attempt to directly apply preference optimization to spoken dialogue models, yet this transfer is non-trivial. We analyze these obstacles from the perspectives of reward modeling and rollout sampling, focusing on how sparse preference supervision interacts with dense speech generation under shared-parameter updates. Based on the analysis, we propose a modality-aware adaptive post-training recipe that makes RL practical for spoken dialogue: it constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring, while dynamically regulating their mixture from rollout statistics to avoid unreliable preference gradients. We evaluate the method across multiple spoken dialogue benchmarks and representative architectures, and observe consistent improvements in semantic quality and speech expressiveness.

Speech enhancement language models achieve strong results when trained on discrete audio tokens, but their optimization relies on token-level cross-entropy rather than the perceptual metrics used for evaluation. We introduce a post-training stage for autoregressive speech enhancement language models using Group Sequence Policy Optimization (GSPO) with multi-metric perceptual rewards. Our method directly optimizes non-differentiable quality metrics (DNSMOS, WER, and UTMOS) as reward signals, without learned surrogates or offline preference pairs. Applied to two autoregressive base models, UniSE and GenSE, our approach achieves state-of-the-art results on the DNS2020 benchmark. A human evaluation ablation further shows that the composite multi-metric reward is preferred over any single-metric variant, confirming that multi-reward optimization avoids the reward hacking observed with single-metric training.

We propose a preference optimization framework with Large Audio-Language Model (LALM) feedback for controllable non-verbal vocalization (NVV) generation in continuous autoregressive speech models. To construct preference data without human preference annotation, we build a bilingual prompt corpus by combining NVV-injected real transcripts with LLM-generated semantically aligned prompts, perform stochastic model rollouts, and use a LALM to rank candidate utterances and form same-prompt chosen--rejected pairs. We then adopt a two-stage optimization strategy: Rejection Sampling Fine-Tuning (RSFT) first adapts the model to LALM-selected high-scoring samples, followed by Anchored Flow-DPO, which formulates pairwise preference optimization using utterance-level flow-matching loss and retains the chosen-sample flow-matching objective as an SFT anchor. This design enables DPO-style preference learning without explicit sequence likelihoods while preserving direct supervision on preferred realizations. On the official 1,600-utterance NVVSpeech Challenge Track~2 test set, our method achieves a Final Track2Score of 75.80 (79.39 ZH / 72.21 EN), outperforming the VoxCPM2 baseline by +1.84. The improvements are mainly driven by higher NVV Accuracy and NVV Perceptual Effect, while Overall Quality remains stable.