:mailbox: Paper Code Collection (Microsoft DKI Group)

This repo hosts multiple open-source codes of the Microsoft DKI LLM Group. You could find the corresponding code as below:

News

• April, 2026: our paper A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research was accepted by ICML 2026.
• April, 2026: our paper RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository was accepted by ACL 2026 (Main) with a Top 15% of accepted papers.
• January, 2026: our paper RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning was accepted by ICLR 2026.
• January, 2025: our paper Self-Evolve Reward Learning for LLMs was accepted by ICLR 2025.

Code Release (Click Title to Locate the Code)

Deep Research

A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research Zhuofan Shi, Ming Ma, Zekun Yao, Fangkai Yang, Jue Zhang, Dongge Han, Victor Rühle, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang. ICML 2026.

RL

Self-Evolved Reward Learning for LLMs Chenghua Huang, Zhizhen Fan, Lu Wang, Fangkai Yang, Pu Zhao, Zeqi Lin, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang, ICLR 2025.

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning Mingrui Wu, Lu Wang, Pu Zhao, Fangkai Yang, Jianjin Zhang, Jianfeng Liu, Yuefeng Zhan, Weihao Han, Hao Sun, Jiayi Ji, Xiaoshuai Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang, Rongrong Ji. ICLR 2026.

Code Gen

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang. ACL 2026 (Main Conference).

Ads

LettinGo: Explore User Profile Generation for Recommendation System Lu Wang, Di Zhang, Fangkai Yang, Pu Zhao, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang. KDD 2025.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Question

If you have any question or find any bug, please go ahead and open an issue. Issues are an acceptable discussion forum as well.

If you want to concat the author, please email: fangkaiyang AT microsoft.com.