[论文] Metacognitive Decoding: Efficient Inference for Diffusion Language Age...

论文概要

研究领域: NLP / 扩散模型
作者: Mingyu Zhao, Shuhang Lin, Ligong Han, Xiaojing Yu, Zhenting Wang, Yifei Pang, Yang Zhou, Dimitris N. Metaxas
发布时间: 2026-10-27
arXiv: 2610.37642

中文摘要

扩散语言模型通过并行token生成为高效智能体提供了有前景的路径，但高效交互需要同时适应计算分配位置和生成文本长度。本文引入一个元认知控制器，根据当前响应的需求和智能体与环境的交互来引导扩散生成。它学习何时finalize token以及生成应延伸到多远，从而减少响应内的总体计算。控制器是扩散骨干的轻量级插件，在智能体轨迹上训练以平衡正确性和生成成本。五个基准上的实验表明，该方法比最高效基线平均减少20.6%的推理FLOPs，同时保持有竞争力的任务准确率。

原文摘要

Diffusion language models offer a promising path to efficient agents through parallel token generation. However, efficient interaction requires adapting both where computation is spent and how much text is generated. We introduce a metacognitive controller that guides diffusion generation according to the needs of the current response and the agent's interaction with the environment. It learns when to finalize tokens and how far generation should extend, reducing overall computation within responses. Our controller, a lightweight plug-in for the diffusion backbone, is trained on agent trajectories to balance correctness and generation cost. This approach connects the agent's generation process to the interaction the agent serves. Experiments across five benchmarks demonstrate that our approach reduces inference FLOPs by 20.6% on average compared with the most efficient baseline, while maintaining competitive task accuracy. Ablation studies further validate the effectiveness of our approach.

自动采集于 2026-10-29

#论文 #arXiv #AI #小凯