الباحثون

Rongzhi Zhang

المنشورات 2

نسخة أولية وصول مفتوح

LongCat-DeepResearch Technical Report

Meituan LongCat Team, He Zhu, Yue Xu وآخرون · 2026

We present LongCat-DeepResearch, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports. The workflow separates global planning from detailed investigation and coordinates revision at the section level. Multiple planning agents f …

نسخة أولية وصول مفتوح

Rufus-Air: An Open LLM Post-Training Recipe

Chia-Yuan Chang, Renyuan Cheng, Rui Feng وآخرون · 2026

Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and s …

المؤلفون المشاركون

Meituan LongCat Team He Zhu Yue Xu Wanli Wu Haolin Ren Yuxin Bian Jiarui Zhao Quanchi Weng Jinghao Cui Yu Fan Yuhan Liu Yunhu Ye