arXiv:2608. 03215v1 Announce Type: cross Abstract: Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead.
arXiv:2509.25050v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where both pre-training and RL post-train...
arXiv:2608.31035v1 Announce Type: new Abstract: Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptu...
arXiv:2606. 09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently.
arXiv:2608.23664v1 Announce Type: cross Abstract: Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing method...
arXiv:2606. 07080v1 Announce Type: cross Abstract: We present dots.
SpeechGym is an audio‑native environment that lets two omni‑modal models converse entirely in native audio, eliminating external ASR/TTS and API boundaries while preserving the tasks, tools, and success checks of a standard text‑based agent benchmark. By training end‑to‑end, the framework addresses perceptual failures—such as misheard arguments that cascade into failed calls—and behavioural failures, both of which are automatically labeled for free. Using per‑turn process rewards to overcome reward sparsity, agents trained in SpeechGym transfer to an independent voice benchmark, doubling task success and improving efficiency in turns and tokens.
The paper investigates why Group Relative Policy Optimization (GRPO) benefits from per‑prompt normalization by examining the local curvature of the sequence‑level policy gradient. It shows that standard deviation normalization acts as an adaptive gradient, yielding a provably faster convergence rate than unnormalized REINFORCE under mild conditions, with the improvement tied to the average within‑prompt reward standard deviation. The authors also propose IS‑GRPO, an importance‑sampling variant that maintains alignment with the full gradient and offers a tighter convergence guarantee, and empirically validate these theoretical insights on GSM8K and MATH datasets at 1.5B and 7B model scales.
arXiv:2609.26536v1 Announce Type: new Abstract: In LLM-based speech translation, transcription-based chain-of-thought (CoT) suffers from a mismatch between reference transcripts used in supervised fi...
arXiv:2608. 06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions.
arXiv:2609.33803v2 Announce Type: replace-cross Abstract: Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate...
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.