# ForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation

arXiv: https://arxiv.org/abs/2609.32448 · HTML: https://mlsanity.com/paper/2609.32448/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning.
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 26 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, 20 of 20)

- [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)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions](https://mlsanity.com/paper/2502.06768/) (2025)
- [SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation](https://mlsanity.com/paper/2510.06303/) (2025)
- [TIP: Token Importance in On-Policy Distillation](https://mlsanity.com/paper/2604.14084/) (2026)
- [wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models](https://mlsanity.com/paper/2507.08838/) (2025)
- [Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective](https://mlsanity.com/paper/2512.03759/) (2025)
- [Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization](https://mlsanity.com/paper/2510.08554/) (2025)
- [Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed](https://mlsanity.com/paper/2512.14067/) (2025)
- [The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models](https://mlsanity.com/paper/2601.15165/) (2026)
- [d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models](https://mlsanity.com/paper/2512.09675/) (2025)
- [Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation](https://mlsanity.com/paper/2606.06712/) (2026)
- [Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding](https://mlsanity.com/paper/2508.19529/) (2025)
- [Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards](https://mlsanity.com/paper/2510.01544/) (2025)
- [Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models](https://mlsanity.com/paper/2510.11683/) (2025)
- [T^star: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning](https://mlsanity.com/paper/2601.11214/) (2026)
- [Learning from the Self-future: On-policy Self-distillation for dLLMs](https://mlsanity.com/paper/2606.18195/) (2026)
- [The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models](https://mlsanity.com/paper/2605.29123/) (2026)

## Built on by (most cited first, 1 of 1)

- [JustOPD: On-Policy Distillation from Autoregressive to Diffusion Language Models](https://mlsanity.com/paper/2610.17397/) (2026)

## Abstract (arXiv)

Autoregressive Next-Token Prediction (NTP) has enabled strong reasoning capabilities in language models, while Diffusion Language Models (DLMs) offer flexible token orders and parallel generation. We ask whether DLMs can acquire NTP-style reasoning through distillation without giving up their native generation process. Direct distillation, however, faces a fundamental mismatch: an autoregressive teacher predicts from a left prefix, whereas a DLM can condition on tokens on both sides. We introduce ForkLeft, a distillation framework that resolves this mismatch by separating the student's rollout from teacher supervision. During training, the student first performs entropy-first rollouts that commit uncertain positions and expose potential forks. We then fix the resulting student prefix and distill an NTP teacher under the same context, with answer correctness determining the supervision source. At inference, the student returns to its native confidence-first parallel decoding. With Qwen3-30B-A3B-Base, ForkLeft improves Efficient-DLM-4B on all ten benchmarks, raising MATH500 from 72.60% to 79.60% and consistently outperforming three alternative designs. The gains scale with teacher strength and generalize to SDAR-4B with only 500 updates. At matched scale, the distilled 4B and 8B students exceed the published SDAR-Chat and OPDLM models on seven benchmarks, showing that DLMs can learn NTP-style reasoning without sacrificing native parallel generation. Code and datasets will be released upon acceptance.