# CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models

arXiv: https://arxiv.org/abs/2609.13060 · HTML: https://mlsanity.com/paper/2609.13060/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning.
- Builds on 27 of its 33 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Placed in

- LLM reasoning / [Diffusion reasoning and test-time scaling](https://mlsanity.com/lr/diffusion-reasoning-and-test-time-scaling/)
- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2504.12216/) (2025)
- [Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning](https://mlsanity.com/paper/2506.06632/) (2025)
- [wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models](https://mlsanity.com/paper/2507.08838/) (2025)
- [BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning](https://mlsanity.com/paper/2506.17211/) (2025)
- [Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models](https://mlsanity.com/paper/2505.10446/) (2025)
- [d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation](https://mlsanity.com/paper/2601.07568/) (2026)
- [d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation](https://mlsanity.com/paper/2509.21474/) (2025)
- [Inpainting-Guided Policy Optimization for Diffusion Large Language Models](https://mlsanity.com/paper/2509.10396/) (2025)
- [Simple Policy Gradients for Reasoning with Diffusion Language Models](https://mlsanity.com/paper/2510.04019/) (2025)
- [Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation](https://mlsanity.com/paper/2606.06712/) (2026)
- [Stabilizing Reinforcement Learning for Diffusion Language Models](https://mlsanity.com/paper/2603.06743/) (2026)
- [Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars](https://mlsanity.com/paper/2602.00612/) (2026)
- [The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check](https://mlsanity.com/paper/2601.12979/) (2026)
- [GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models](https://mlsanity.com/paper/2605.29398/) (2026)
- [Learnability-Informed Fine-Tuning of Diffusion Language Models](https://mlsanity.com/paper/2605.22939/) (2026)
- [How Transparent is DiffusionGemma?](https://mlsanity.com/paper/2606.20560/) (2026)
- [Mask-Aware Policy Gradients for Diffusion Language Models](https://mlsanity.com/paper/2607.15200/) (2026)
- [TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models](https://mlsanity.com/paper/2604.00666/) (2026)

## Abstract (arXiv)

Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use tasks. While Reinforcement Learning (RL) has recently been applied to enhance DLMs, standard RL approaches suffer from an exploration bottleneck. To address this, we inject reasoning priors from a stronger teacher model to guide RL exploration. In this paper, we introduce CanvasAnneal, a curriculum-guided diffusion RL framework. During the initial RL phase, we warm-start exploration by injecting teacher-generated reasoning traces into the initial diffusion canvas. As training progresses, we gradually remove this guidance and require the model to generate more of the reasoning trajectory independently. Across mathematical reasoning and tool-use benchmarks, CanvasAnneal improves over standard diffu-GRPO on MATH500, Countdown, and Tau2 and substantially accelerates reward improvement on several tasks, while gains are task-dependent. Our results suggest that structured training-time guidance can alleviate exploration bottlenecks in diffusion RL and speed up convergence on harder tasks.