My research broadly focuses on large language models (LLMs), spanning:

• RL-based Post-Training & Reasoning — developing reinforcement learning frameworks that strengthen LLM reasoning, including small–large LLM collaboration.
• LLM Agents & Multi-Agent Collaboration — coordinating heterogeneous LLM agents to solve tasks jointly and efficiently.
• Efficient Fine-Tuning & Deployment — enabling LLM fine-tuning and inference in distributed and on-device settings under computation, communication, and memory constraints.
• Distributed Optimization — designing efficient and convergent optimization algorithms for distributed machine learning.

• Oct 2026 I expect to graduate in Spring 2027 and am on the job market, seeking research scientist and machine learning engineer positions. Feel free to reach out via email or see my CV.
• Sep 2026 Two papers accepted to NeurIPS 2026: Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs and PAAC: Privacy-Aware Agentic Device-Cloud Collaboration.
• Jun 2026 Joined the AI Center at Samsung Research America (SRA) as an NLP/ML Research Intern, working on LLM reasoning and multi-agent systems.
• Apr 2026 Two papers accepted to ICML 2026: Bridging On-Device and Cloud LLMs for Collaborative Reasoning and Federated Sketching LoRA.

Selected First-Author Publications (full list)

NeurIPS2026	Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs Wenzhi Fang, Liangqi Yuan, Guangchen Lan, Dong-Jun Han, Christopher G. Brinton Advances in Neural Information Processing Systems (NeurIPS), 2026
Preprint2026	Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA Wenzhi Fang, Nicholas Tzou, Lazar Valkov, Srinivas Chappidi arXiv preprint, 2026
ICML2026	Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Wenzhi Fang, Dong-Jun Han, Liangqi Yuan, Evan Chen, Christopher G. Brinton International Conference on Machine Learning (ICML), 2026
ICML2026	Federated Sketching LoRA: On-Device Collaborative Fine-Tuning of Large Language Models Wenzhi Fang, Dong-Jun Han, Liangqi Yuan, Seyyedali Hosseinalipour, Christopher G. Brinton International Conference on Machine Learning (ICML), 2026
Preprint2026	Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints Evan Chen*, Wenzhi Fang*, Shiqiang Wang, Christopher G. Brinton arXiv preprint, 2026
ToN2025	Federated Learning over Hierarchical Wireless Networks: Training Latency Minimization via Submodel Partitioning Wenzhi Fang, Dong-Jun Han, Christopher G. Brinton IEEE/ACM Transactions on Networking, 2025
NeurIPS2024	Hierarchical Federated Learning with Multi-Timescale Gradient Correction Wenzhi Fang, Dong-Jun Han, Evan Chen, Shiqiang Wang, Christopher G. Brinton Advances in Neural Information Processing Systems (NeurIPS), 2024
TSP2022	Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning Wenzhi Fang, Ziyi Yu, Yuning Jiang, Yuanming Shi, Colin N. Jones, Yong Zhou IEEE Transactions on Signal Processing, 2022

Selected Collaborative Publications (full list)

Preprint2026	Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination Liangqi Yuan, Wenzhi Fang, Shiqiang Wang, Christopher G. Brinton arXiv preprint, 2026
NeurIPS2026	PAAC: Privacy-Aware Agentic Device-Cloud Collaboration Liangqi Yuan, Wenzhi Fang, Shiqiang Wang, Christopher G. Brinton Advances in Neural Information Processing Systems (NeurIPS), 2026
Preprint2025	TAP: Two-Stage Adaptive Personalization of Multi-task and Multi-Modal Foundation Models in Federated Learning Seohyun Lee, Wenzhi Fang, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher G. Brinton arXiv preprint, 2025

• fang375@purdue.edu