cs.LGFeb 2, 2026

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

Authors: Ziwei Luo, Ziqi Jin, Lei Wang, Lidong Bing, Thomas B. Schön

Organizations: Uppsala University, Sweden · MiroMind AI, Singapore · Nanyang Technological University, Singapore

Abstract

This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our algorithm stems from the observation that most existing MDLMs rely on a confidence-based sampling strategy, where only tokens with the highest prediction confidence are preserved at each step. This restricts the generation to a noise-sensitive, greedy decoding paradigm, resulting in an inevitable collapse in the diversity of possible paths. We address this problem by launching multiple interacting diffusion processes in parallel, referred to as particles, for trajectory exploration. Importantly, we introduce the trajectory-level confidence as a self-rewarding signal for assigning particle importance weights. During sampling, particles are iteratively weighted and resampled to systematically steer generation towards globally confident, high-quality samples. Our self-rewarding SMC is verified on various masked diffusion language models and benchmarks, achieving significant improvement without extra training or reward guidance, while effectively converting parallel inference capacity into improved sampling quality. Our code is available at https://github.com/Algolzw/self-rewarding-smc.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding

    Oct 19, 2026Minoo Ahmadi, Seyedarmin Azizi, Mehdi Kamal +1Language Model DecodingDiffusion Language Model Decoding

  2. Improving Sampling for Masked Diffusion Models via Information Gain

    Feb 20, 2026Kaisen Yang, Jayden Teoh, Kaicheng Yang +2Diffusion SamplingDiffusion Language Model Decoding