Yubo Dong

ZHEJIANG UNIVERSITY

Yubo Dong 董玉博

PhD student · Research on reasoning and autonomous agents

I am a PhD student at Zhejiang University, since 2023, advised by Prof. Hehe Fan. I study how language models can organize their reasoning, investigate difficult questions with evidence, and collaborate as agents.

I collaborate with Ant Group on research (September 2025 – October 2026) and serve as a reviewer for ACL 2026 and ICLR 2027.

Research

First-authored and coauthored work.

EMNLP 2026 Unreleased manuscript

MessageSieve

Runtime Message Pruning for Accurate and Efficient LLM-Based Multi-Agent Communication

Yubo Dong et al.

SIGGRAPH Asia 2026 Accepted

StructSVG

Tree-Graph Guided Multi-Agent Text-to-SVG Generation

Yubo Dong et al.

Super Research paper overview

arXiv 2026 First author

Super Research

Answering Highly Complex Questions with Large Language Models through Super Deep and Super Wide Research

Yubo Dong, Nianhao You, Yuxuan Hou, Zixun Sun, Yue Zhang, Liang Zhang, Siyuan Zhao, Hehe Fan

A benchmark for complex autonomous research through deep investigation and broad evidence gathering.

Structured Reasoning paper overview

ICLR 2026 First author

Structured Reasoning

Structured Reasoning for LLMs: A Unified Framework for Efficiency and Explainability

Yubo Dong, Hehe Fan

Explicit reasoning-step structure for efficient and explainable language models.

Dataset and project materials available; training code and checkpoints not yet released.

Hi-Lo Prune paper overview

CVPR 2026 Second author

Hi-Lo Prune

Look at What You'll Lose before Pruning with Hierarchical Token Selection

Zixun Sun, Yubo Dong, Hehe Fan, Yi Yang

Efficient vision-language inference through hierarchical token selection and information merging.

Project information available; implementation not yet released.

VillagerAgent paper overview

ACL 2024 First author

VillagerAgent

A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft

Yubo Dong, Xukun Zhu, Zhengzhe Pan, Linchao Zhu, Yi Yang

Coordinating collaborative agents through explicit task graphs in Minecraft.

Experience & service

Sep 2025 – Oct 2026
Ant Group

Research collaboration

Academic service
Conference reviewer

ACL 2026 · ICLR 2027

Honors