Jinyu Xiang
Algorithm Researcher at Xiaomi Mimo-Core · AI Agent Researcher · Musician
I am an Algorithm Researcher at Xiaomi Mimo-Core, working on large models for reasoning, coding, and agents. Previously, I co-founded Karis, spearheading the algorithm team in advancing the core capabilities of General Agents. I was also a Researcher at MetaGPT (DeepWisdom), and initiated OpenManus with the team. My research focuses on LLM-based Agents, particularly Agent Self-Evolution and Foundation Agents.
I am also the Research Lead at Agent Universe, leading team research on AI content reformulation and redistribution.
Besides my work in AI, I am an Independent Musician on Tencent Music, creating instrumental music, Traditional Chinese style (Gufeng), and Electronic music, with over 2 million plays and 1k+ followers.
News
- Joined Xiaomi Mimo-Core as an Algorithm Researcher.
- Released Open Research, an AI-powered research assistant that goes from idea to full paper. Generated 7 research papers spanning AI agents, astrophysics, and philosophy.
- CoFounded Karis, focusing on General Agents and Marketing Agent applications.
- Participated in the Foundation Agent Survey V1, exploring cross-environment agents.
- Proposed and built OpenManus with the team, achieving 50K+ Stars!
- Self-Supervised Prompt Optimization was accepted by EMNLP 2025.
- AFLOW was accepted by ICLR 2025 as an Oral Presentation (Top 1.8%).
Selected Publications
AFlow: Automating Agentic Workflow Generation
AFlow introduces an automated framework that reformulates workflow optimization as a search problem over code-represented workflows, using Monte Carlo Tree Search to efficiently explore and refine workflows through code modification and execution feedback.
Self-Supervised Prompt Optimization
We propose a self-supervised framework for prompt optimization that enables language models to automatically refine prompts through iterative feedback and learning.
OpenManus: An Open-Source Framework for Building General AI Agents
OpenManus is a minimalist Agent framework that articulates the minimal structural units for Agent design. We completed this project in just three hours, which garnered 35k stars within its first week of release.
Advances And Challenges In Foundation Agents
A comprehensive survey on Foundation Agents with universal understanding, cognition, and action capabilities that can operate in any environments and collaborate to form collective intelligence.
Job Experience
- Algorithm Researcher, Xiaomi Mimo-Core, China.
- CoFounder, Karis, China.
- Researcher, DeepWisdom, China.
- Research Lead, Agent Universe, China.
- Independent Musician, Tencent Music, China.
Competitions and Side Projects
- Open Research, Author. An AI-powered research assistant that autonomously conducts end-to-end research — from literature review to experimentation to paper writing. Generated 7 full papers across AI, astrophysics, and philosophy.
- OpenManus, Github 50K+ stars, Founder. Proposed and assembled a team to recreate Manus functionality, completing the project in just three hours, which garnered 35k stars within its first week.
- Zhihu AI Social Experiment, Author. Conducted a social experiment by creating a fully autonomous AI account on Zhihu that posted content for a month without human intervention or detection.
- 2024 Alibaba Global Mathematics Competition AI Challenge, Top 1% (2/563), Author. Developed the MathAI multi-agent system to tackle Olympiad level math problems, reaching the finals and placing second.
Invited Talks
- Weibo AI Deep Talk #27: Is AI Entrepreneurship a Traffic Password?
- INCLUSION·Conference on the Bund Roundtable: Industry Observations from a Gen-Z Agent Application Entrepreneur
- Tencent: The Second Half of AI - Defining Problems is More Important Than Solving Them
- Tencent: The Explosive Rise of Agents - Unlimited Application Space?
Recent Blog Posts
-
End-of-2025 Reflections: Thoughts on Agents
An end-of-year reflection centered on Agent Learning/Evolving, methodologies for AI products, industry competition and long-term moats, and how people rewire “rewards” amid uncertainty.