Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models

arXiv:2608.01717 · cs.LG · Submitted 2026-08-03 · Read on arXiv

cs.LG

Submitted: 2026-08-03

Updated: 2026-09-17

Code: https://github.com/Jiayi-Pan/TinyZero

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 50× in this paper · explained in 2 episodes
• Accuracy — 39× in this paper · explained in 1 episode
• Reinforcement Learning — 26× in this paper · explained in 4 episodes
• Fine-Tuning — 10× in this paper · explained in 5 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• GRPO — 3× in this paper · explained in 6 episodes
• Reasoning Traces — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Block Diffusion — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Dream 7B: Diffusion Large Language Models
• wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
• Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
• SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
• dKV-Cache: The Cache for Diffusion Language Models
• Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
• Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
• DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
• Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
• DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
• Inpainting-Guided Policy Optimization for Diffusion Large Language Models
• Understanding R1-Zero-Like Training: A Critical Perspective
• Qwen3 Technical Report
• Evaluating Large Language Models Trained on Code

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks