精选理由
可以把扩散模型当成真智能体用，规划工具自己纠错，解码还比自回归快，不试试？
LLaDA 2.2 是首个大规模扩散语言模型，能够作为智能体自主完成规划、工具调用和错误修正。它在长多轮对话轨迹中保持稳定表现，并凭借块并行解码实现更快推理速度。该模型标志着扩散模型从静态生成向主动代理任务的关键跨越。
原文 · elvis
Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM b...
Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning, calling tools, and self-correcting across long multi-turn trajectories, and it keeps the speed advantage of block-parallel decoding. Lots of technical decisions here that stand out: 💬 4 🔄 4 ❤️ 8 👀 2078 📊 6 ⚡