Multi-Agent Evaluation
What makes a good team of agents?
Evaluating how agent teams coordinate, where they fail, and what collective performance reveals beyond individual capability.
RESEARCH NOTEBOOKSHANGHAI · CHINA
Qiran Zhang.
Learning through interaction.
Thinking together.
Understanding intelligence.
I am an undergraduate student in Artificial Intelligence at Shanghai Jiao Tong University, working with Prof. Chen Qian (钱忱) at AAIL.
My research interests center on the evaluation of multi-agent systems, collaborative intelligence, and reinforcement learning.
Research Threads
Current questions
Collaborative Intelligence
How does intelligence become collective?
Understanding how communication, shared knowledge, and complementary roles help agents solve problems together.
Reinforcement Learning
Learning from actions and each other
Exploring how interaction, feedback, and learning shape decision-making and cooperation in multi-agent systems.
Selected Work
All publications
CerebraGloss: Instruction-Tuning a Large Vision-Language Model for Fine-Grained Clinical EEG Interpretation
An EEG-text instruction data engine, CerebraGloss-Bench, and a large vision-language model for generative clinical EEG interpretation.
PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning
A benchmark for testing whether language models can write runnable code that also preserves spatial and temporal coherence.
AcademiClaw: When Students Set Challenges for AI Agents
A bilingual benchmark of long-horizon academic tasks, sourced from real student workflows rather than simplified prompts.
Notes
CerebraGloss accepted to ICLR 2026.
PRISM and AcademiClaw released as public research benchmarks.
SIDE B / 研究之外
On repeat.一些反复听的声音。
「人潮擁擠握住濕熱的手心」2002 ↗吉他手
陳綺貞 / Cheer Chen
「於是你不停散落，我不停拾獲」2012 ↗神的遊戲
張懸 / Deserts Chang
happy happy
誰想要sad:))— 一起去度假
「聽也聽不到的聲音，你卻要我仔細聽」2025 ↗
如果每天都可以 happy happy 誰想要sad:))— 一起去度假
陳嫺靜 / Hsien Ching
留給這一頁的聲音
此刻，心裡有一首歌。
找一首歌，或寫下仍留在心裡的那一句。
便箋只留在你的瀏覽器。搜尋由 Apple iTunes 提供。
頁間收藏
還空著，等你放進第一首歌。
Contact
I welcome conversations about multi-agent evaluation, collaborative intelligence, and reinforcement learning.