Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science
arXiv:2602.05289 · Submitted to NeurIPS 2026
Autonomous Agents · Multi-Agent Systems · LLM Interpretability
I am an undergraduate researcher at Fudan University, majoring in Intelligent Science and Technology. My research focuses on autonomous agents, multi-agent systems, large language models, and AI interpretability.
Currently, I am working on the scientific evaluation of LLM-based multi-agent systems, agent workflow reconstruction, and mechanistic interpretability for foundation models. My long-term goal is to build AI systems that are not only capable, but also scientifically understandable, controllable, and trustworthy.
Agent design, tool use, self-improvement, evaluation, and deployment in complex reasoning environments.
Scientific evaluation of collaboration, factor-controlled MAS analysis, communication, topology, and coordination.
Feature explanations, causal effects, SAE-based analysis, and agent-assisted diagnosis of model behavior.
Developed a scientific evaluation framework for LLM-based multi-agent systems, including a collaboration-gain metric that separates genuine cooperation from resource scaling and a factor library for controlled MAS analysis.
Building a two-sided feature explanation framework that connects input-side SAE activations with output-side causal effects, assisted by self-evolving agents for diagnosis and adaptive optimization.
Contributed to discussions and experiments for reconstructing black-box agent workflows into editable white-box systems using combinatorial search over agent roles, models, reasoning modes, and tools.
arXiv:2602.05289 · Submitted to NeurIPS 2026
ICML 2026
GPA: 3.88/4.0; Rank: 1/27. Core coursework includes programming, data structures and algorithms, computer architecture, and statistical learning.
Outside research, I enjoy badminton, detective fiction, board games, and meeting people from different backgrounds. I am always open to friendly conversations, research discussions, and new collaborations.