You can also find my articles on my Google Scholar profile.
* denotes equal contribution. † denotes project lead.
2026
-
Bridging Databases and Documents: Data-Algorithm Co-Design for Hybrid Question Answering
Ruofan Wu, Boyi Liu, Fan Shu, Yite Wang, Zhewei Yao, Yuxiong He, and Feng Yan
In COLM, 2026
RL DataAgent RL TrainingBenchmark
-
-
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Junbo Li, Boyi Liu, Canwen Xu, Yite Wang, Zhewei Yao, Zhangyang Wang, Qiang Liu, and Yuxiong He
In COLM, 2026
Auto Research
-
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Zhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang, Siwei Han, Zhewei Yao, Huaxiu Yao, and Yuxiong He
In ICML, 2026
RL DataAgent RL Training
-
DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science
Fan Shu*, Yite Wang*†, Ruofan Wu, Boyi Liu, Zhewei Yao, Yuxiong He, and Feng Yan
In ICLR, 2026
RL DataAgent RL TrainingBenchmark
-
Learning to Self-Evolve
Xiaoyin Chen, Canwen Xu, Yite Wang, Boyi Liu, Zhewei Yao, Yoshua Bengio, and Yuxiong He
In Lifelong Agent Workshop at ICLR, 2026
RL TrainingTest-time Adaptation
-
Defer Consensus: Long-horizon Multi-Agent Deep Research with Diverse Priors
Soyoung Yoon, Boyi Liu, Yite Wang, Ruofan Wu, Canwen Xu, Nikki Lijing Kuang, Zhewei Yao, Seung-won Hwang, and Yuxiong He
Under review, 2026
Swarm AgentDeep Research
-
PersonalClaw: Evaluating and Training Personalized AI Assistants with Synthetic Work Environments
Sida Li, Xiaodong Yu, Boyi Liu, Yite Wang, Zhewei Yao, and Yuxiong He
Under review, 2026
Agent TrainingOpenClaw Agent
-
PRISM-DS: Closing the Task-Profile-to-Skill Loop for Data-Science Agents
Fan Shu, Yite Wang, Ruofan Wu, Boyi Liu, Zhewei Yao, Yuxiong He, and Feng Yan
Under review, 2026
Data Science Agent
-
Evaluating Open-Web Research Agents with Structured Exploration Maps
Youngwon Lee, Soyoung Yoon, Yexiao He, Yite Wang, Boyi Liu, Zhewei Yao, Ang Li, Seung-won Hwang, and Yuxiong He
Under review, 2026
Deep ResearchEvaluation
-
Routing with Memory: Test-Time Adaptation without Fine-Tuning
Ziyue Li, Boyi Liu, Canwen Xu, Yite Wang, Zhewei Yao, Tianyi Zhou, and Yuxiong He
Under review, 2026
Model Routing
2025
-
FullStack Bench: Evaluating LLMs as Full-Stack Coders
ByteDance Seed-Foundation-Code Team
Preprint, 2025
Evaluation
-
Efficient Large Foundation Model Inference: A Perspective from Model and System Co-Design
Dong Liu*, Zhixin Lai*, Yite Wang*, Jing Wu*, Yanxuan Yu, Zhongwei Wan, Benjamin Lengerich, and Ying Nian Wu
Preprint, 2025
SurveyEfficiency
2024
-
LEMON: Lossless Model Expansion
Yite Wang, Jiahao Su, Hanlin Lu, Cong Xie, Tianyi Liu, Jianbo Yuan, Haibin Lin, Ruoyu Sun, and Hongxia Yang
In ICLR, 2024
Model Expansion
2023
-
Balanced Training for Sparse GANs
Yite Wang*, Jing Wu*, Naira Hovakimyan, and Ruoyu Sun
In NeurIPS, 2023
Pruning
-
NTK-SAP: Improving Neural Network Pruning by Aligning Training Dynamics
Yite Wang, Dawei Li, and Ruoyu Sun
In ICLR, 2023
Pruning
2022
-
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
Haoxiang Wang*, Yite Wang*, Ruoyu Sun, and Bo Li
In CVPR, 2022
Neural Architecture SearchNTK
2019
-
Numerical Investigation of Convective Transport in Redox Flow Battery Tanks: Using Baffles to Increase Utilization
Yite Wang, and Kyle Smith
Journal of Energy Storage, 2019
Computational Physics