一作ACL 2026Poster· Natural Language Processing
The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check
Qingyu Lu · Liang Ding · Kanjian Zhang · Jinxia Zhang · Dacheng Tao
摘要
The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break the sequential latency bottleneck. However, does such efficiency gains translate into effective agentic behavior? In t...