Mingfei Lu
01 — About

Hi, I'm Mingfei. 👋

I'm a PhD student at the University of Technology Sydney, advised by Prof. Yi Zhang. My research is on Multi-Agent Systems and Agent Memory for large language models — broadly, how should agents remember, reason, and coordinate so that they actually help people?

Always happy to chat about agent memory architectures, multi-agent systems, and legal agentic systems. Reach out →

Multi-Agent Systems Agent Memory LLM Reasoning Legal NLP Agentic Systems
02 — News

🔥 What's new

  1. 2026
    New preprint: Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection — diffusion-guided learning for few-shot graph fraud detection.
  2. 2026
  3. 2026
    New preprint: Choosing How to Remember: Adaptive Memory Structures for LLM Agents — a framework (FluxMem) that lets agents pick the right memory structure per context. +9.18% / +6.14% on PERSONAMEM / LoCoMo.
  4. 2025
    From Newborn to Impact: Bias-Aware Citation Prediction accepted to The Web Conference 2026 🎉
  5. 2025
    Joined UTS as a PhD student under Prof. Yi Zhang. Research focus: agent memory and multi-agent reasoning.
03 — Research

📝 Selected Publications

ACL 2026 first author multi-agent

From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation

Mingfei Lu, Yi Zhang, Mengjia Wu, Yue Feng.

Annual Meeting of the Association for Computational Linguistics (ACL Main), 2026. CCF-A

We construct JurisCQAD, a large-scale, expert-verified dataset of 43,000 real-world Chinese legal consultation entries, and propose JurisMA, a modular multi-agent framework based on legal element graphs that supports dynamic routing, statute alignment, and style optimization. JurisMA significantly outperforms both general-purpose and legal-domain LLM baselines on LawBench.

WWW 2026 first author graph learning

From Newborn to Impact: Bias-Aware Citation Prediction

Mingfei Lu, Mengjia Wu, Jiawei Xu, Weikai Li, Feng Liu, Ying Ding, Yizhou Sun, Jie Lu, Yi Zhang.

Proceedings of the ACM Web Conference (WWW), 2026, pp. 7600–7609. CCF-A

A bias-aware citation prediction framework addressing the challenge of forecasting impact for newly published papers under sparse early citation signals and long-tail distributions. By combining multi-agent feature extraction with robust graph representation learning, the model reduces MALE / RMSLE by ~13% and improves NDCG by 5.5%.

Under review first author agent memory

Choosing How to Remember: Adaptive Memory Structures for LLM Agents

Mingfei Lu, Mengjia Wu, Feng Liu, Jiawei Xu, Weikai Li, Hao Wang, Zhen Hu, Ying Ding, Yizhou Sun, Jie Lu, et al.

arXiv preprint arXiv:2602.14038, 2026.

Existing agent memory systems use a one-size-fits-all structure and don't treat structure selection as a context-adaptive decision. We propose FluxMem, which equips agents with multiple complementary memory structures and learns to pick among them per interaction, with a three-level hierarchy and a Beta-Mixture-Model probabilistic gate replacing brittle similarity thresholds. +9.18% on PERSONAMEM, +6.14% on LoCoMo.

For the live citation count, see my Google Scholar.

04 — Education

📖 Education

  • Jan 2025 — present
    Ph.D. in Artificial Intelligence, University of Technology Sydney
    Australian Artificial Intelligence Institute (AAII) · Advisor: Prof. Yi Zhang
05 — Teaching

👩‍🏫 Teaching

  • Feb 2025 — present
    Academic Tutor · Computer Science Studio 1 (41078)
    Faculty of Engineering and Information Technology, University of Technology Sydney
06 — Service

🤝 Academic Service

Reviewer for:

WWW 2026 ICWSM 2026 EMNLP 2026 AAAI 2025 NeurIPS 2025 Scientometrics Knowledge-Based Systems