AI模型也能接力跑：谁更靠谱谁领跑
大模型生成答案时，不同模型在不同阶段各有优劣。研究者发现，一个模型在生成过程中，如果对答案关键位置的置信度保持稳定，说明它走在靠谱的路径上；反之则可能出错。基于此，他们设计了一种“接力”方法：让多个模型同时生成，实时追踪每个模型在关键位置上的置信度变化，选出当前最靠谱的那个，把它的部分生成结果传给其他模型继续。这样，不同模型可以在不同阶段贡献自己的优势，最终答案更准确。在多个推理任务上，这种方法比单个模型或简单集成效果更好。它不是你明天就能用上的工具，但展示了未来AI协作的一种可能：不是让一个模型包揽一切，而是让多个模型像接力赛一样，谁状态好谁领跑。
📄 原文摘要(英文)
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.