Qwen3.5: Towards Native Multimodal Agents
Qwen Team
Blog · Models
A native multimodal model family with powerful agent capabilities.

Qwen3-Coder: Agentic Coding in the World
Qwen Team (Core Contributor)
Blog · Code · Models
Focused on improving agentic coding capabilities.

Qwen3-Coder-Next: Pushing Small Hybrid Models on Agentic Coding
Qwen Team (Core Contributor)
Blog · PDF · Code · Model
A local-first agentic coding model based on Qwen3-Next.

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Zhoujun Cheng*, Shibo Hao*, Tianyang Liu*, Fan Zhou, Feng Yao, Yuexin Bian, Yutao Xie, ... , Nilabjo Dey, Yonghao Zhuang, Yuheng Zha, Yi Gu, Kun Zhou, Yuqi Wang, Yuan Li, Richard Fan, Jianshu She, Chengqian Gao, Abulhair Saparov, Taylor W. Killian, Haonan Li, Mikhail Yurochkin, Eric P. Xing, Zhengzhong Liu, Zhiting Hu (*=equal contribution) [more authors]
NeurIPS 2025.
PDF · Code · Dataset
GURU: An open RL suite for developing general-purpose reasoning models.

OctoThinker: Mid-Training Incentivizes RL Scaling
Zengzhi Wang*, Fan Zhou*, Xuefeng Li, Pengfei Liu
ICML 2025, AI4Math Workshop.
PDF · Blog · Code · Resources
A mid-training ablation study in the era of RL scaling, with a 70+B token mid-training dataset.

MegaMath: Pushing the Limits of Open Math Corpora
Fan Zhou*, Zengzhi Wang*, Nikhil Ranjan, Zhoujun Cheng, Liping Tang, Guowei He, Zhengzhong Liu, Eric P. Xing
COLM 2025.
PDF · Code · Dataset (>70K Downloads, >350B Tokens)
The largest open math pre-training dataset with 370B tokens.

Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale
Fan Zhou*, Zengzhi Wang*, Qian Liu, Junlong Li, Pengfei Liu, (*=equal contribution)
ICML 2025
PDF · Code · Dataset (>10K Downloads, >500B Tokens) · Project Page
A small-LLM-based pre-training data refining framework via seamless program generation.

OpenAgents: An Open Platform for Language Agents in the Wild
Tianbao Xie*, Fan Zhou*, Zhoujun Cheng*, Peng Shi*, Luoxuan Weng*, Yitao Liu*, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, Tao Yu, (*=equal contribution)
COLM 2024
PDF · Code · Blog (7.5K Users)
An open platform for using, hosting, and building language agents.

Lemur: Harmonizing Natural Language and Code for Language Agents
Yiheng Xu*, Hongjin Su*, Chen Xing*, Boyu Mi, Qian Liu, Weijia Shi, Binyuan Hui, Fan Zhou, Yitao Liu, Tianbao Xie, Zhoujun Cheng, Siheng Zhao, Lingpeng Kong, Bailin Wang, Caiming Xiong, Tao Yu, (*=equal contribution)
ICLR 2024, Spotlight
PDF · Code · Models · Blog
A 70B language agent model pre-trained on balanced code and text corpora.