🌟 A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Yizhang ZHU, Liangwei WANG, Chenyu YANG, Xiaotian LIN, Boyan LI, Wei ZHOU, Xinyu LIU, Zhangyang PENG, Tianqi LUO, Yu LI, Chengliang CHAI, Chong CHEN, Shimin DI, Ju FAN, Ji SUN, Nan TANG, Fugee TSUNG, Jiannan WANG, Chenglin WU, Yanwei XU, Shaolei ZHANG, Yong ZHANG, Xuanhe ZHOU, Guoliang LI, Yuyu LUO

🔥 Survey 🤗 HF Daily Top 3

[Paper] [Paper List & Repo] [Slides]

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

Jingze SHI, Zhangyang PENG, Yizhang ZHU, Yifan WU, Guang LIU, Nan TANG, Yuyu LUO

ICML 2026

[Paper] [Code]

DeepEye: A Steerable Self-driving Data Agent System

Boyan LI, Yiran PENG, Yupeng XIE, Sirong LU, Yizhang ZHU, Xing MU, Xinyu LIU, Yuyu LUO

🥈 Silver Medal at the International Exhibition of Inventions Geneva 🏆 Best Open-source Project Award at AI Agent 2025 Competition

SIGMOD 2026 Demo

[Homepage] [Paper] [Code] [Awards]

Concise Math Reasoning via Difficulty-Aware Distillation

Yifan WU, Jingze SHI, Bingheng WU, Jiayi ZHANG, Xiaotian LIN, Yizhang ZHU, Zhaoyang YU, Bang LIU, Chenglin WU, Nan TANG, Yuyu LUO

ACL 2026 Findings

[Paper] [Code]

A Survey of Agentic Materials Science and Engineering: Where Are We and Where Are We Going?

Jiayi ZHU, Longhan ZHANG, Yizhang ZHU, Xiaotian LIN, Yifan WU, Shimin DI, Bang LIU, Yuyu LUO, Tongyi ZHANG

Journal of Materials Informatics

[Paper]

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

Xiaotian LIN, Yanlin QI, Yizhang ZHU, Themis Palpanas, Chengliang CHAI, Nan TANG, Yuyu LUO

VLDB 2026

[Paper] [Code]

Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights

Yifan WU, Lutao YAN, Yizhang ZHU, Yinan MEI, Jiannan WANG, Nan TANG, Yuyu LUO

ArXiv

[Paper]

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing

Yizhang ZHU, Runzhi JIANG, Boyan LI, Nan TANG, Yuyu LUO

COLM 2025

[Homepage] [Paper] [Code]

SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

Teng LIN, Yizhang ZHU, Yuyu LUO, Nan TANG

ArXiv

[Paper] [Code]

RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition

Xudong YANG, Yizhang ZHU, Nan TANG, Yuyu LUO

IJCAI 2025

[Paper] [Code]

AskChart: Universal Chart Understanding through Textual Enhancement

Xudong YANG, Yifan WU, Yizhang ZHU, Nan TANG, Yuyu LUO

ArXiv

[Paper] [Code]

Are Large Language Models Good Statisticians?

Yizhang ZHU, Shiyin DU, Boyan LI, Yuyu LUO, Nan TANG

NeurIPS 2024

[Homepage] [Paper] [Code] [Video]