Advancing Intelligence Frontiers

QuantaAlpha

Elite AI Agent Research Team πŸš€
Building the future of Autonomous Intelligence

Explore Research Collaboration
20+
Publications
30+
Researchers
April 2025
Founded
PKU β€’ THU β€’ UCAS β€’ CMU β€’ HKUST β€’ Stanford β€’ ZJU
Top Affiliations

Research Focus

Agent Intelligence

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, synthesizing insights across domains.

Agentic RL

Reasoning-centered reinforcement learning, bridging decision-making, planning, and adaptive intelligence.

Self-Evolving

Agents that continuously improve through self-evolution and collaborative learning, enabling emergent collective intelligence.

AI4Science

AI4Investment

Agent-driven automated investment: discovering optimal factors, strategies, and execution models for intelligent trading and portfolio management.

AI4Healthcare

Efficiency-first AI for healthcare: scalable foundation models, vision-language alignment, and agentic workflows for real-world clinical impact.

AI4Bioinformatics

Agent-driven discovery in genomics: automating bioinformatics analyses and enabling novel scientific insights in biological research.

Featured Publications

Highlighted papers, swipe to explore more

All Publications (20+)

Complete publication list

2026

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

LLM Reasoning Adaptive Cognitive Modes Chain of Mindset
Paper Code
2026

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

AI4Investment self-evolving Alpha Mining
Paper Code
2026

Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening

Agent Safety Intrinsic Risk Sensing Hierarchical Defense
Paper Code
2026

Controlled Self-Evolution for Algorithmic Code Optimization

Self-Evolution CodeAgent Genetic Algorithm EffiBench
Paper Code
2026

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

CodeAgent Memory Bug Fixing SWE-bench
Paper Code
2026

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Video Reasoning DeepResearch Web Retrieval VideoDR
Paper Code
2026

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

Agent Memory Person Understanding Digital Companion
Paper Code
2026

EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines

Self-Evolution DeepResearch Finite State Machine Multi-hop QA
arXiv
2026

FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

Agent Safety Financial Security Regulatory Compliance
arXiv Code
2026

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

Agent Memory Graph Structure Dialog Memory
arXiv
2026

CloneMem: Benchmarking Long-Term Memory for AI Clones

Agent Memory AI Clone Temporal Reasoning
Paper Code
2026

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

Agent Memory Cross-session Dialog Real-world Interaction
Paper Code
2026

DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation

LoRA MoE Dynamic Rank PEFT
arXiv
2025

πŸ™ Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration

Multimodal Reasoning Agentic Framework arXiv Preprint
Paper
NeurIPS 2025

🧠 SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning

Self-Evolution Trajectory Optimization Poster
Paper Code
AAAI 2026 Oral

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

CodeAgent Benchmark Oral
Paper Code
EMNLP 2025 Findings

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast&Slow Reasoning for Robust Agent Defense

Agent Safety Self-learning Hierarchical Reasoning
Paper Code
NeurIPS 2025 Spotlight

πŸ” RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories

CodeAgent Repository Understanding Spotlight
Paper Code
ACL 2025 Findings

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs

LLM Safety Essence Driven Defense Jailbreak
Paper Code
2025

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs

LLM Safety Self-learning Jailbreak
Paper

Latest News

Team updates and paper acceptance

2025.12
πŸ† Paper "GitTaskBench" accepted to AAAI 2026 as Oral!
2025.11
πŸŽ‰ "Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration" on arXiv!
2025.10
πŸ† Paper "RepoMaster" accepted to NeurIPS 2025 as Spotlight!
2025.10
πŸ† Paper "SE-Agent" accepted to NeurIPS 2025 Poster!
2025.10
πŸŽ‰ "ALRPHFS" accepted to Findings of EMNLP 2025.
2025.05
πŸŽ‰ "Beyond Surface-Level Patterns..." accepted to Findings of ACL 2025.
2025.02
πŸ“„ "ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs" released on arXiv.

Our Team

Meet the researchers behind QuantaAlpha

HW

Huacan Wang

wanghuacan17@mails.ucas.ac.cn
RC

Ronghao Chen

chenronghao@alumni.pku.edu.cn
SH

Sen Hu

husen@pku.edu.cn
SZ

Shuo Zhang

mcflurryshuoz@gmail.com
BW

Biao Wu

biaowu165534@gmail.com
ZL

Zaoqu Liu

liuzaoqu@163.com
ZT

Zhenheng Tang

zhtang.ml@ust.hk
JL

Jingping Liu

liujp68@mail.sysu.edu.cn
QL

Qizhen Lan

contact.gai4si@gmail.com
ZY

Zhi Yang

yangzhi@stu.sufe.edu.cn
XY

Xiaomin Yu

yuxm02@gmail.com
ZC

Ziming Cheng

e1554503@u.nus.edu
TH

Tu Hu

tuhu@smail.nju.edu.cn
CY

Chaofa Yuan

bruceyuan123@gmail.com
CY

Ruichuan An

arctanxarc@gmail.com

Join Our Community

Engage with us on WeChat and XiaoHongShu for real-time discussions

Personal WeChat

Harry_-_Wang
WeChat ID

Add for direct communication with the team core.

Academic Exchange

WeChat QR

Scan to join our vibrant research community group.

XiaoHongShu

QuantaAlpha
Like-minded Community
Click to Copy Link

Follow our updates on RED.

Collaboration & Careers

We are always looking for exceptional talent and partners.

Seeking Partners

  • β€’ University/Corp Labs: Joint research, compute resources.
  • β€’ Startups: Industry applications of Agent tech.
  • β€’ Open Source: Contributors for our GitHub repos.

Ideal Candidate

  • β€’ Top-tier conference publications (First Author).
  • β€’ Strong self-motivation & passion for AGI.
  • β€’ Focus: Agentic RL, CodeAgents, Reasoning.
quantaalpha.ai@gmail.com

Reach out to explore unlimited possibilities.