← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-long.1723 · 记录 #1
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 21:50
摘要
Diffusion large language models (dLLMs) generate text by repeatedly unmasking a partially noised sequence in parallel, promising lower latency than autoregressive decoding. However, most discrete dLLMs still rely on fixed denoising schedules, which are non-adaptive to input difficulty and cannot learn efficient unmasking orders. This paper introduces a reinforcement learning (RL) framework that transforms dLLM decoding into a trajectory-aware, learnable policy. We propose a confidence-gated denoising strategy that dynamically decides which tokens to unmask and how many to unmask per step, enabling adaptive exploration of denoising trajectories. Building on Group Relative Policy Optimization, we reformulate it into a trajectory-aware variant, TA-GRPO-d, which combines a trajectory-level signal—captured as the z-score of the AUC over intermediate rewards—with a token-level unmasking-time weight. This design allows the model to learn not only the final output quality but also the efficiency of the decoding path itself. Experiments on MATH-500, Countdown, Sudoku, and code benchmarks (HumanEval, MBPP) show that TA-GRPO-d maintains or improves accuracy while reducing average denoising steps by up to half, achieving both faster inference and lower computational cost. Our approach provides an RL framework for optimizing dLLM decoding policies toward adaptive, efficient reasoning. Code is available at our GitHub.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs
Diffusion large language models (dLLMs) generate text by repeatedly unmasking a partially noised sequence in parallel, promising lower latency than autoregressive decoding. However, most discrete dLLMs still rely on fixed denoising schedules, which are non-adaptive to input difficulty and cannot learn efficient unmasking orders. This paper introduces a reinforcement learning (RL) framework that transforms dLLM decoding into a trajectory-aware, learnable policy. We propose a confidence-gated denoising strategy that dynamically decides which tokens to unmask and how many to unmask per step, enabling adaptive exploration of denoising trajectories. Building on Group Relative Policy Optimization, we reformulate it into a trajectory-aware variant, TA-GRPO-d, which combines a trajectory-level signal—captured as the z-score of the AUC over intermediate rewards—with a token-level unmasking-time weight. This design allows the model to learn not only the final output quality but also the efficiency of the decoding path itself. Experiments on MATH-500, Countdown, Sudoku, and code benchmarks (HumanEval, MBPP) show that TA-GRPO-d maintains or improves accuracy while reducing average denoising steps by up to half, achieving both faster inference and lower computational cost. Our approach provides an RL framework for optimizing dLLM decoding policies toward adaptive, efficient reasoning. Code is available at our GitHub.
查看此版本解读 →查看此版本原文 ↗