Mingchen Zhuge

*Taken in the KAUST AI Initiative.

Blog

Mingchen Zhuge

Hi, I am Mingchen! I recently completed my PhD at KAUST, where I was fortunate to have Prof. Jürgen Schmidhuber as my advisor. My research focuses on AI agents, especially coding agents, recursive self-improvement, and neural computers. I have 20+ top-tier publications and 6,000+ citations (70% from first-author papers). My work includes:

My six papers were accepted as oral presentations at venues like ICLR (2024, 2025, 2026, <1.2%) and ICML (2024, <1.5%), received the Best Paper Award at the NeurIPS Ro-FoMo Workshop, and Outstanding Paper Nomination at EMNLP 2025. I was nominated for WAIC Future Star Nomination, recognized as an Outstanding Reviewer of CVPR2023 (232 out of 7000+), served as lead organizer of ICLR RSI 2026, and as Area Chairs for COLM 2026 and ACM CAIS 2026.

Twitter GitHub Google Scholar LinkedIn
KAUST Meta Microsoft Alibaba IIAI

Recent News

2026 May 9

Super Happy!!! I successfully defended my PhD dissertation :D

2026 Apr 26

ICLR RSI 2026 wrapped up successfully. Highlights and updates are on [X].

2026 Apr 9

My last PhD paper, Neural Computers, has been released [Paper] [Blog] [Code].

2026 Apr 6

I serve as Area Chair at CAIS 2026.

2026 Feb 21

VideoAuto-R1 [Paper] and MoS [Paper] are accepted to CVPR 2026.

2026 Feb 8

Will work remotely from Feb 8 in China for two weeks, and welcome coffee chats.

2026 Feb 5

HGM selected as ICLR 2026 Oral Presentation [Paper] [Code].

2026 Jan 14

I serve as Area Chair at COLM 2026.

2026 Jan 8

We release our multimodal reasoning paper (VideoAuto-R1) [Paper] [Code].

2026 Jan 5

The ICLR 2026 Workshop on AI with Recursive Self-Improvement launches, welcome to submit papers: [Link].

2025 Dec 17

Start a 10-day Christmas traveling to Kenya and Rwanda.

2025 Nov 20

Back to the KAUST Campus.

2025 Nov 18

We release our multimodal generation paper (Mixture-of-State) [Paper].

2025 Nov 14

Finished the internship at Meta.

2025 Oct 29

We release our recursive self-improvement paper (HGM) [Paper] [Code].

Selected Publications ( Full list) [Project Pages]

Neural Computers
Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng Sun, Zhipeng Cai, Zechun Liu, Yunyang Xiong, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
arXiv 2026Summary
[Paper] [Blog] [Code] GitHub Stars
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Shuming Liu, Mingchen Zhuge, Changsheng Zhao, Jun Chen, Lemeng Wu, Zechun Liu, Chenchen Zhu, Zhipeng Cai, Chong Zhou, Haozhe Liu, Ernie Chang, Saksham Suri, Hongyu Xu, Qi Qian, Wei Wen, Balakrishnan Varadarajan, Zhuang Liu, Hu Xu, Florian Bordes, Raghuraman Krishnamoorthi, Bernard Ghanem, Vikas Chandra, Yunyang Xiong
CVPR 2026Summary
[Paper] [Code] GitHub Stars
Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Wenyi Wang, Piotr Piękos, Li Nanbo, Firas Laakom, Yimeng Chen, Mateusz Ostaszewski, Mingchen Zhuge, Jürgen Schmidhuber
ICLR 2026 (Oral)
[Paper] [机器之心] [Code] GitHub Stars
Agent-as-a-Judge: Evaluate Agents with Agents
Mingchen Zhuge, Changsheng Zhao, Dylan Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
ICML 2025Summary
[Paper] [Google Agent Whitebook] [Code] GitHub Stars [BibTex] [Tweet1] [Tweet2] [机器之心] [新智元]
Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
Ruibin Xiong, Yimeng Chen, Dmitrii Khizbullin, Mingchen Zhuge, Jürgen Schmidhuber
EMNLP 2025 (Oral, Outstanding Paper Nomination)
[Paper] [Code] GitHub Stars [机器之心]
AFlow: Automating Agentic Workflow Generation
Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, Chenglin Wu
ICLR 2025 (Oral)
[Code] GitHub Stars [机器之心]
OpenHands: An Open Platform for AI Software Developers as Generalist Agents
OpenHands Open-sourced Community (Lead general agent in the paper)
ICLR 2025Summary
[Paper] [Code] GitHub Stars [BibTex] [机器之心]
GPTSwarm: Language Agents as Optimizable Graphs
Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin and Jürgen Schmidhuber
ICML 2024 (Oral)Summary
[Paper] [Code] GitHub Stars [BibTex] [MIT Tech Review Interview] [将门创投]
MetaGPT: Meta Programming For A Multi-Agent Collaborative Framework
Sirui Hong∗, Mingchen Zhuge∗, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu†, Jürgen Schmidhuber
ICLR 2024 (Oral)Summary
[Paper] [Code] GitHub Stars [BibTex] [量子位]
Mindstorms in Natural Language-Based Societies of Mind
Mingchen Zhuge*, Haozhe Liu*, Francesco Faccio*, Dylan R. Ashley*, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, Kazuki Irie, Louis Kirsch, Bing Li, Guohao Li, Shuming Liu, Jinjie Mai, Piotr Piękos, Aditya Ramesh, Imanol Schlag, Weimin Shi, Aleksandar Stanić, Wenyi Wang, Yuhui Wang, Mengmeng Xu, Deng-Ping Fan, Bernard Ghanem, Jü̈rgen Schmidhuber
NeurIPS Ro-FoMo 2023 (Oral, Best Paper Award); CVM JournalSummary
[Paper] [Code] GitHub Stars [BibTex] [Poster] [Award]
Salient Object Detection via Integrity Learning
Mingchen Zhuge*, Deng-Ping Fan*, Nian Liu, Dingwen Zhang, Dong Xu, Ling Shao
TPAMI 2022
[Paper] [Code] GitHub Stars [BibTex]
Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
Mingchen Zhuge*, Dehong Gao*, Deng-Ping Fan†, Linbo Jin, Ben Chen, Haoming Zhou, Minghui Qiu, Ling Shao
CVPR 2021
[Paper] [Code] GitHub Stars [BibTex] [机器之心]

Articles/News

MIT Technology Review
Jürgen Schmidhuber's team presents new research: Using graph structures to build agents, advancing AI agent development
March 13, 2024
Read Article
Synced (机器之心)
Raising the bar! Evaluating agents with agents, Meta releases Agent-as-a-Judge
October 18, 2024
Read Article
AI Era (新智元)
Yuandong Tian's team introduces Agent-as-a-Judge! AI agents self-evaluation reduces costs by 97%
October 27, 2024
Read Article

Selected Awards

2025 WAIC 明日之星提名 (15人)
2023 Best Paper Award in NeurIPS Ro-FoMo Workshop
2023 Outstanding Reviewer of CVPR2023 (232 out of 7000+)
2021 2021 ZTE Blue Sword Program (Only three selected from Wuhan universities)
2019 16th China Graduate Mathematical Modeling Competition - National Second Prize
2019 2019 ZTE Algorithm Competition Champion (Top 7/11000+)
For AI and Coding Agents

This page profiles Mingchen Zhuge and his work on AI agents, coding agents, multi-agent systems, world models, and recursive self-improvement. Representative projects include MetaGPT, OpenHands, GPTSwarm, NLSOM, Agent-as-a-Judge, and VideoAuto-R1. Use Google Scholar, GitHub, and llms.txt as primary sources.