Haidong Xin

Haidong Xin

NEUIR & TsinghuaNLP

👋 I am currently pursuing an M.S. in Computer Science at Northeastern University. My research interests include NLP, information retrieval, Retrieval-Augmented Generation, recommender systems, and multi-agent systems. You can find my Google Scholar profile here .

🎓 I received my B.S. in Computer Science from Harbin Engineering University. I am now a master’s student at NEUIR Lab, advised by Associate Professor Zhenghao Liu. I also collaborate closely with Qiyuan Lab Qiyuan Lab, ModelBest ModelBest, and TsinghuaNLP TsinghuaNLP, and am mentored by Associate Researcher Yukun Yan.

🔥 We sincerely invite you to try and contribute to our new project, UltraRAG v3!

🔥 Feedback, ideas, and contributions are always welcome.

Page Views: · Last Updated: 2026-03-22 · hdxin2002@gmail.com

🔥 News

  • 2026.02:  🎉 Our paper Knowledge Intensive Agents has been accepted by AI Open (IF=14.8)!
  • 2026.01:  🎉 UltraRAG v3 reached #2 on GitHub Trending!
  • 2026.01:  🎉 We released UltraRAG v3, making every step of the reasoning workflow visible!
  • 2025.11:  🎉 Our paper LISRec has been accepted at KDD 2026 (CCF-A)!
  • 2025.11:  🎉 We released UltraRAG v2.1 with multimodal support and a more unified evaluation pipeline!
  • 2025.08:  🎉 We released UltraRAG v2, a low-code framework for building complex RAG systems!
  • 2025.08:  🎉 Our paper TASTE$^+$ has been accepted at WISA 2025 and selected for an oral presentation!
  • 2025.08:  🎉 Our paper LLMsPark has been accepted at EMNLP 2025 (CCF-B)!
  • 2024.04:  🎉 We released the GitHub repository heu-icicles and warmly invite you to contribute!
  • 2024.02:  🎉 Our paper MMAD has been accepted at COLING 2024 (CCF-B)!
  • 2023.05:  🎉 Our paper received an Honorable Mention at MCM/ICM 2023!

📝 Publications

* indicates equal contribution, and † indicates corresponding author.

ArXiv 2026
MetaMem paper figure

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization

Haidong Xin$^{*}$, Xinze Li$^{*}$, Zhenghao Liu$^†$, Yukun Yan$^†$, Shuo Wang, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun

arXiv GitHub Repo Stars

This work proposes MetaMem, a meta-memory framework that evolves meta-memory through self-reflective symbolic optimization, enabling knowledge utilization in long-horizon human-LLM interactions.

ArXiv 2026
PAGER paper figure

Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation

Xinze Li, Zhenghao Liu$^†$, Haidong Xin, Yukun Yan$^†$, Shuo Wang, Zheni Zeng, Sen Mei, Ge Yu, Maosong Sun

arXiv GitHub Repo Stars

This work enhances RAG systems by constructing structured cognitive outlines to guide iterative retrieval, effectively organizing multi-dimensional knowledge into coherent pages for more accurate answer generation.

KDD 2026
LISRec paper figure

LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation

Haidong Xin, Zhenghao Liu$^†$, Sen Mei, Yukun Yan, Shi Yu, Shuo Wang, Zulong Chen, Yu Gu, Ge Yu, Chenyan Xiong

arXiv GitHub Repo Stars

This work improves sequential recommendation systems by extracting personalized semantic shortcuts from user-item interaction histories, enhancing the capture of stable user preferences.

AI Open
Knowledge Intensive Agents survey figure

Knowledge Intensive Agents

Zhenghao Liu, Pengcheng Huang, Zhipeng Xu, Xinze Li, Shuliang Liu, Chunyi Peng, Haidong Xin, Yukun Yan$^†$, Shuo Wang, Xu Han, Zhiyuan Liu$^†$, Maosong Sun$^†$, Yu Gu, Ge Yu

DOI

This work provides a comprehensive overview of Retrieval-Augmented Generation from an agentic perspective, categorizing knowledge-intensive agents into acquisition and utilization roles, and highlighting future directions for joint optimization in multi-agent RAG systems.

WISA 2025
TASTE+ paper figure

Adapting Language Models to Text Matching based Recommendation Systems

Haidong Xin, Sen Mei, Zhenghao Liu$^†$, Xiaohua Li, Minghe Yu, Yu Gu, Ge Yu

DOI GitHub Repo Stars

This work has significantly improved the performance of text matching in recommendation systems by incorporating language model pretraining.

EMNLP 2025
LLMsPark paper figure

LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts

Junhao Chen, Jingbo Sun, Xiang Li, Haidong Xin, Yuhao Xue, Yibin Xu, Hao Zhao$^†$

arXiv

This work introduces LLMsPark, a game theory-based platform for evaluating large language models’ strategic behaviors and decision-making abilities in multi-agent environments, providing a novel criterion for assessing their intelligence.

COLING 2024
MMAD paper figure

MMAD: Multi-modal Movie Audio Description

Xiaojun Ye, Junhao Chen, Xiang Li, Haidong Xin, Chao Li, Sheng Zhou$^†$, Jiajun Bu

ACL Anthology GitHub Repo Stars

This work has unlocked a whole new experience of watching movies for the visually impaired.

MCM/ICM 2023
MCM/ICM paper figure

Puzzle Game: Prediction and Classification of Wordle Solution Words

Haidong Xin$^{*†}$, Fang Wu$^{*}$, Zhitong Zhou$^{*}$

arXiv

This work conducted a detailed numerical analysis of the Wordle game, revealing statistical patterns within it.

🏆 Awards

  • 2025.11 🥇 First-Class Excellent Student Scholarship.
  • 2024.11 🥇 First-Class Excellent Student Scholarship.
  • 2023.07 🥈 National Second Prize, Chinese Collegiate Computing Competition (4C 2023).
  • 2023.05 🥈 Honorable Mention, Mathematical Contest in Modeling (MCM/ICM 2023).
  • 2023.05 🥈 Second Prize, China International College Students’ Innovation Competition.
  • 2022.11 🥇 First Prize, China Undergraduate Mathematical Contest in Modeling (CUMCM 2022).
  • 2022.10 🥈 Second Prize, Mathematical Modeling Competition of the Three Northeastern Provinces.
  • 2022.05 🥇 First-Class Excellent Student Scholarship.
  • 2021.05 🥇 First-Class Excellent Student Scholarship.

📖 Education

💬 Media Mentions

💻 Research and Internships