Work

T⋆: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning

Year: 2026

Type: conference-paper

Abstract: We present T ⋆ , a simple TRACERL-based curriculum for progressive block-size scaling in masked diffusion language models (MDMs).Starting from an AR-initialized small-block MDM, T ⋆ gradually increases the block size while re-optimizing the denoising policy at each stage, enabling higher-parallelism decoding with limited degradation on math reasoning benchmarks.Across two SDAR scales and three benchmarks, T ⋆ consistently outperforms direct large-block TRACERL and is substantially more stable during training.Our schedule analysis suggests that the learned policy does not simply revert to a strictly left-to-right order; instead, it retains block-size-specific nonmonotone updates while improving accuracy.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-short.67

Authors: Hanchen Xia, Baoyou Chen, Yutang Ge, Guojiang Zhao, Siyu Zhu

Institutions: Fudan University, Shanghai Innovation Institute, Shanghai Jiao Tong University, Carnegie Mellon University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Natural Science Foundation of Shanghai, Shanghai Municipal Commission of Economy and Informatization

OpenAlex ID: W7166884110