👋 About Me

I am currently a member of the LongCat Team at Meituan, focusing on large language models, including post-training, model evaluation, and agentic systems.

I received my M.S. degree from Southeast University in 2019 and my B.S. degree from Jiangnan University in 2016. My research interests span LLMs, deep learning, and knowledge graphs.

Feel free to reach out if you are interested in collaboration!

🔥 News

• [2026-01] Our R-Horizon has been accepted to ICLR 2026. We release R-Horizon, which is a novel benchmark and training recipe for RLVR on long-horizon reasoning. 🔥
• [2026-01] We release EvoCUA, which focuses on GUI agent and achieves SOTA performance (56.7%) through all open-weights models on OS-World leaderboard. 🔥
• [2025-03] Our team won the Gold Medal in Kaggle WSDM Cup - Multilingual Chatbot Arena. 🏅
• [2024-10] Our team achieved 2nd Place in RecSys 2024 EKSTRA BLADET News Recommendation Challenge. 🎉
• [2024-10] Our paper "Calibrating the Confidence of Large Language Models by Eliciting Fidelity" has been accepted by EMNLP 2024. 🎉
• [2024-08] Our team won the Silver Medal in Kaggle Home Credit Credit Risk Stability Challenge. 🏅

🔬 Research Interests

• Large Language Models: Post Training, Model Evaluation, and Agentic Systems.
• Deep Learning: Representation Learning, and Neural Architecture Design.
• Knowledge Graphs: Entity Recognition, Information Extraction, and BQA.

📝 Publications

1. LongCat-Next: Lexicalizing Modalities as Discrete Tokens
   Meituan LongCat Team
   arXiv, 2026 Paper
2. LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
   J Wang, J Zhang, Q Guo, L Guo, R Li, et al.
   arXiv, 2026 Paper
3. Advancing Block Diffusion Language Models for Test-Time Scaling
   Y Lu, D Kong, J Wang, L Guo, X Wang, et al.
   arXiv, 2026 Paper
4. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
   T Xue, C Peng, M Huang, L Guo, T Han, et al.
   arXiv, 2026 Paper
5. LongCat-Flash-Thinking-2601 Technical Report
   Meituan LongCat Team
   arXiv, 2026 Paper
6. R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
   Y Lu, J Wang, L Guo, W He, H Tang, et al.
   ICLR, 2025 Paper
7. Introducing LongCat-Flash-Thinking: A Technical Report
   Meituan LongCat Team
   arXiv, 2025 Paper
8. LongCat-Flash Technical Report
   Meituan LongCat Team
   arXiv, 2025 Paper
9. Calibrating the Confidence of Large Language Models by Eliciting Fidelity
   M Zhang, M Huang, R Shi, L Guo, C Peng, P Yan, Y Zhou, X Qiu
   EMNLP, 2024 Paper
10. Large Scale Hierarchical User Interest Modeling for Click-through Rate Prediction
    T Xue, Z Lin, Z Zhang, L Guo, H Chen, M Bao, P Yan
    RecSys Challenge, 2024 Paper
11. Unsupervised Latent Event Representation Learning and Storyline Extraction from News Articles Based on Neural Networks
    J Si, L Guo, D Zhou
    Intelligent Data Analysis, 2021 Paper
12. Storyline Extraction from News Articles with Dynamic Dependency
    L Guo, D Zhou, Y He, H Xu
    Intelligent Data Analysis, 2020 Paper
13. Neural Storyline Extraction Model for Storyline Generation from News Articles
    D Zhou, L Guo, Y He
    NAACL, 2018 Paper

🎖 Awards

• 2025 — Kaggle WSDM Cup - Multilingual Chatbot Arena, Gold Medal
• 2024 — RecSys EKSTRA BLADET News Recommendation Challenge, 2nd Place
• 2024 — Kaggle Home Credit Credit Risk Stability Challenge, Silver Medal
• 2018 — SemEval Multilingual Emoji Prediction, 12th/333

📖 Education

• 2016.09 - 2019.06
  M.S., Southeast University
• 2012.09 - 2016.06
  B.S., Jiangnan University