# TIE：基于轨迹的掩码扩散语言模型集成框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-15 08:00
- AIHOT 分数：44
- AIHOT 链接：https://aihot.virxact.com/items/cmqg30by7032cslspsv9heeqf
- 原文链接：https://arxiv.org/abs/2606.16281

## AI 摘要

研究发现掩码扩散语言模型（MDLM）中，成功的生成在答案相关位置呈现稳定置信度动态，不可靠轨迹可通过注入其他模型的中间状态纠正。基于此，提出TIE（Trajectory-based Iterative Ensembling）框架，通过追踪置信度动态识别可靠解码轨迹并在模型间传递部分去噪序列，使不同模型在不同生成阶段贡献互补优势。在多种推理任务上取得强性能，为MDLM集成提供了实用方案。

## 正文

Masked Diffusion Language Models (MDLMs) have emerged as a distinct paradigm for sequence generation. As MDLMs become diverse in capabilities and knowledge coverage, an important question is how to combine their knowledge. Toward this, we first investigate the unique decoding dynamics of MDLMs. We find that successful generations exhibit stable confidence dynamics over answer-relevant positions, while unreliable trajectories can often be corrected by injecting promising intermediate states from other models. Guided by this observation, we propose TIE (Trajectory-based Iterative Ensembling), a knowledge fusion framework in which MDLMs iteratively identify reliable decoding trajectories and relay them across models. TIE tracks confidence dynamics over answer-relevant positions to determine which model currently follows a more reliable trajectory and selectively transfers partially denoised sequences across models. As the model on the more promising trajectory often changes across denoising steps, TIE allows different models to contribute complementary strengths at different stages of generation. Strong performance across diverse reasoning tasks, along with our analyses, suggests that TIE offers a practical approach to the underexplored problem of MDLM ensembling.