# 腾讯混元发布 UniRL 统一多模态强化学习基础设施及 DRPO/Flow-DPPO 两种新算法，支持跨模态单一 RL 循环训练

- 来源：Tencent Hunyuan
- 发布时间：2026-06-09 19:45
- AIWatch 分数：73
- AIWatch 标记：当日精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01ktvxhzxws6ac8y260wf88d3j
- 原文链接：https://x.com/TencentHunyuan/status/2064312869827809702

## 精选理由

高信息密度，值得细读

## AI 摘要

现有RL框架多针对单模态设计。腾讯混元开源UniRL，提供统一多模态强化学习基础设施，通过单一后训练循环覆盖扩散/流匹配模型、LLM/VLM及统一多模态模型。同步推出DRPO与Flow-DPPO两种原创算法，支持可插拔推理引擎与FSDP2扩展。开发者可用一套基础设施跨模态进行RL后训练，降低多模态模型对齐成本。
核心观点：
1. UniRL以单一RL循环（generate→score→advantage→update→sync）覆盖扩散/流匹配、LLM、VLM及统一多模态模型，模型与算法为独立轴。
2. Flow-DPPO基于精确散度为流匹配/扩散模型引入信任域掩码策略优化；DRPO为LLM RL引入平滑的优势加权二次正则化。
3. 基础设施支持train-side、SGLang、vLLM-Omni三种可插拔rollout引擎，并内置FSDP2分片与单配置三部署模式。

## 正文

One RL loop across diffusion/flow matching models, LLMs/VLMs, and unified multimodal models👇

Code: http://github.com/Tencent-Hunyuan/UniRL

(yes — U(you)-ni-(need) RL 😉)

1、Most RL stacks are built for one modality. UniRL applies a single post-training loop — generate → score → advantage → update → sync — across model families. Model and algorithm are two independent axes, so your coverage is the model × algorithm product, not a fixed recipe menu.

2、One loop, every modality: text→image, text/image→video, vision-language, text-only LLM and VLM, the LLM→diffusion prompt-enhancer, and unified autoregressive+diffusion generation (Hunyuan-Image 3 and Bagel) — a model class no single-purpose RL repo can even express.

3、Built to scale: pluggable rollout engines (train-side / SGLang / vLLM-Omni) behind one typed contract, FSDP2 sharding, and three deployment modes from a single config knob.

4、Two team-original algorithms headline the release:

FlowDPPO: Policy optimization for flow/diffusion models with trust-region masks based on exact divergence (See our paper: Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models https://github.com/Tencent-Hunyuan/UniRL/blob/main/FlowDPPO/HY_FlowDPPO.pdf)

DRPO: LLM RL with a smooth, advantage-weighted quadratic regularizer
(See our paper: Rethinking the Divergence Regularization in LLM RL [https://arxiv.org/abs/2606.09821])