1
Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction
提出动态混合精度路由方法，在多步LLM交互中实现高效推理，在精度与效率间取得平衡。
arXiv:2602.02711v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks thro…