DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning

• URL: http://arxiv.org/abs/2510.02212v1
• Date: Thu, 02 Oct 2025 16:57:24 GMT
• Title: DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
• Authors: Hanyang Zhao, Dawen Liang, Wenpin Tang, David Yao, Nathan Kallus,
• Abstract summary: We propose a unified framework for training masked diffusion large language models (dLLMs) to reason better (furious)<n>We first unify the existing baseline approach by proposing to train surrogate policies via off-policy RL, whose likelihood is much more tractable as an approximation to the true dLLM policy.<n>We also propose a new direction of joint training efficient samplers/controllers of dLLMs policy. Via RL, we incentivize dLLMs' natural multi-token prediction capabilities by letting the model learn to adaptively allocate an inference threshold for each prompt.
• Score: 37.20873499361773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furious), but also faster via reinforcement learning (RL). We first unify the existing baseline approach such as d1 by proposing to train surrogate policies via off-policy RL, whose likelihood is much more tractable as an approximation to the true dLLM policy. This naturally motivates a more accurate and informative two-stage likelihood approximation combined with importance sampling correction, which leads to generalized RL algorithms with better sample efficiency and superior task performance. Second, we propose a new direction of joint training efficient samplers/controllers of dLLMs policy. Via RL, we incentivize dLLMs' natural multi-token prediction capabilities by letting the model learn to adaptively allocate an inference threshold for each prompt. By jointly training the sampler, we yield better accuracies with lower number of function evaluations (NFEs) compared to training the model only, obtaining the best performance in improving the Pareto frontier of the inference-time compute of dLLMs. We showcase the effectiveness of our pipeline by training open source large diffusion language models over benchmark math and planning tasks.

Related papers

• Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers [55.33468902405567]
  We propose a new learning paradigm, In-Context Preference-based Reinforcement Learning (ICPRL), in which both pretraining and deployment rely solely on preference feedback.<n>ICPRL enables strong in-context generalization to unseen tasks, achieving performance comparable to ICRL methods trained with full reward supervision.
  arXiv  Detail & Related papers  (2026-02-09T03:42:16Z)
• DiRL: An Efficient Post-Training Framework for Diffusion Language Models [54.405206032785706]
  Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models.<n>Existing methods suffer from computational inefficiency and objective mismatches between training and inference.<n>We introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference.
  arXiv  Detail & Related papers  (2025-12-23T08:33:19Z)
• Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization [44.14678335188207]
  Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs)<n>Reinforcement learning (RL) is a crucial component for dLLMs to achieve comparable performance with AR-LLMs on important tasks, such as reasoning.<n>This paper proposes Distribution Matching Policy Optimization (DMPO), a principled and theoretically grounded RL fine-tuning method.
  arXiv  Detail & Related papers  (2025-10-09T13:59:50Z)
• Principled and Tractable RL for Reasoning with Diffusion Language Models [0.0]
  Diffusion large language models (dLLMs) are trained to predict multiple tokens in parallel and generate text via iterative unmasking.<n>Recent works have successfully pretrained dLLMs to parity with autoregressive LLMs at the 8B scale, but dLLMs have yet to benefit from modern post-training techniques.<n>We present Amortized Group Relative Policy Optimization (AGRPO), a principled on-policy RL algorithm designed specifically for dLLMs.
  arXiv  Detail & Related papers  (2025-10-05T03:53:16Z)
• CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs [53.749193998004166]
  Curriculum learning plays a crucial role in enhancing the training efficiency of large language models.<n>We propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead.
  arXiv  Detail & Related papers  (2025-10-01T15:41:27Z)
• Learning to Reason as Action Abstractions with Scalable Mid-Training RL [55.24192942739207]
  An effective mid-training phase should identify a compact set of useful actions and enable fast selection.<n>We propose Reasoning as Action Abstractions (RA3), a scalable mid-training algorithm.
  arXiv  Detail & Related papers  (2025-09-30T05:34:20Z)
• Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle [53.239242017802056]
  Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM)<n>However, current RL pipelines often suffer from training inefficiencies caused by two underexplored issues: Advantage Collapsing and Rollout Silencing.<n>We propose Shuffle-R1, a simple yet principled framework that improves RL fine-tuning efficiency by dynamically restructuring trajectory sampling and batch composition.
  arXiv  Detail & Related papers  (2025-08-07T17:53:47Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning [31.531278643184656]
  Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL)<n>We propose d1, a framework to adapt pre-trained masked dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL.<n>We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM.
  arXiv  Detail & Related papers  (2025-04-16T16:08:45Z)
• DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training [19.701565022644605]
  We present a principled curriculum learning framework grounded in the notion of distribution-level learnability.<n>Our framework prioritizes distributions with either high average advantage (exploitation) or low sample count (exploration)<n>Our experiments show that our framework significantly improves convergence speed and final performance.
  arXiv  Detail & Related papers  (2025-04-13T20:10:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.