💬 WeChat

QuantaAlpha Logo QuantaAlpha

Elite AI Agent Research Team • Advancing Intelligence Frontiers 🚀

👥 Team Profile
Founded: April 2025
Members: 20+ Researchers
Affiliations:
Universities: UCAS, Tsinghua, PKU, CMU, HKUST, USTC, ZJU, etc.
Roles: Professors (985/211), Postdocs, PhD/Master Students
Committed to pushing AI Agent technology frontiers
🔬 Research Focus
💻 CodeAgent: End-to-end execution for real-world coding tasks
📚 DeepResearch: Multi-step reasoning for scientific discovery
🧠 Agentic RL: Reasoning-centered reinforcement learning
🔄 Self-Evolving: Continuous improvement & co-learning
Code Agent
Deep Research
Agentic RL
Self-Evolving

💬 WeChat Contact

$ cat social_communities.md

Join our vibrant communities for real-time discussions and collaboration! 🚀

👤 Personal WeChat Contact

💬
Harry_-_Wang
WeChat ID

Add for direct communication

🏘️ Academic Exchange Group

WeChat Group QR Code

Scan to join our research community

📖 XiaoHongShu Group

📱
QuantaAlpha
志同道合处
Click to Copy
Expires: 9/27

Join our XiaoHongShu community

🔬
Research Discussions
Latest AI Agent insights
🤝
Collaboration
Find research partners
📚
Resource Sharing
Papers & tools exchange

💡 Pro Tip: Join our WeChat group for instant updates and engage directly with our research team!

📧 Collaboration

$ cat collaboration_opportunities.md

We are actively seeking collaborators and team members who share our passion for AI Agent technology. 🤝

🔗 Collaboration Resources We Need:

  • 🏫 University/Corporate Lab Resources: API access, GPU resources, and academic influence
  • 📚 Academic Research Collaboration: Joint research projects and publications
  • 💻 GitHub Open Source Collaboration: Contributing to and maintaining open-source projects
  • 🚀 Startup Collaboration: Industry partnerships and real-world applications
$ echo $IDEAL_TEAM_MEMBER

👥 Ideal Team Member Profile:

  • 🧮 Strong Algorithmic Capabilities: Published at least one A-class conference paper as first author
  • 💪 Exceptional Self-Motivation: Ultimate pursuit of technology and academia
  • 📖 Research Experience: Paper and achievement accumulation in Agent and LLM directions
  • 🎯 Research Focus: RL + Agentic Reasoning / CodeAgent / DeepSearch

📧 Contact: quantaalpha.ai@gmail.com
✨ Let's explore the unlimited possibilities of AI Agent technology together!

2025.11

🎉 Check out our latest work: "Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration" on arXiv!

2025.11

🎊 Exciting news! Three papers accepted at AAAI 2026, including two orals!

2025.09

🎊 Exciting news! Two papers accepted at NeurIPS 2025, including one spotlight!

2025.08

🎉 Check out our latest work: "GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging" on arXiv!

2025.08

🎉 Check out our latest work: "CogFSM: Enabling Explicit and Capability-aware Multi-Agent Systems with Self-Learning Finite State Machines" on arXiv!

2025.08

🎉 Check out our latest work: "SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents" on arXiv!

2025.05

🎉 Check out our latest work: "RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving" on arXiv!

2025.04

🚀 QuantaAlpha team officially established, dedicated to cutting-edge AI Agent technology research!
Octopus Paper

🐙 Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration

QuantaAlpha Team
📄 arXiv Preprint
📖 Paper | 💻 GitHub (Coming Soon)

SE-Agent Paper

🧠 SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents

QuantaAlpha Team
📄 arXiv Preprint
📖 Paper | 💻 GitHub

GitTaskBench Paper

🧩 GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging

QuantaAlpha Team
📄 arXiv Preprint
📖 Paper | 💻 GitHub

RepoMaster Paper

🔍 RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

QuantaAlpha Team
📄 arXiv Preprint
📖 Paper | 💻 GitHub

🔬 Research Areas

$ ls -la research_areas/
  • 💻 CodeAgent:
    End-to-end execution for real-world coding tasks, enabling agents to autonomously understand, modify, and run complex repositories.
  • 📚 DeepResearch:
    Multi-step reasoning agents for open-ended scientific and knowledge discovery, capable of synthesizing insights across domains.
  • 🧠 Agentic Reasoning / Agentic RL:
    Scaling reinforcement learning with reasoning-centered agents, bridging decision-making, planning, and adaptive intelligence.
  • 🔄 Self-Evolving & Co-Learning:
    Agents that continuously improve through self-evolution and collaborative learning, enabling emergent collective intelligence.
$ cat tech_stack.md
Python
JavaScript
AI Agents
Deep Learning
Code Analysis
Reinforcement Learning