• Hello! My name is Jianing Wang (王嘉宁).
• I obtained the Ph.D degree at East China Normal University (ECNU) (from Sep. 2019 to Jun. 2024) in Shanghai supervised by Prof. Ming Gao, Prof. Xiang Li, and Prof. Yunshi Lan majoring Deep Learning and Natural Language Processing (NLP). I also visited at UCSD and supervised by Prof. Julian McAuley from Oct. 2023 to Feb. 2024. Now, I am a full-time staff engineering in Meituan
• My research points consist of Large Language Models (LLMs), Post-training for LLMs (SFT and RLVR), Formal Reasoning, and Agentic Learning. If you want to join us, please send an email to me.
• I have published some research papers (30+) at ICLR, ACL, AAAI, EMNLP, CIKM, etc., the topic includes Thinking Pattern Research for LLMs, Formal Theorem Proving, Long-horizon with RLVR, Few-shot Leanrning and Prompt Learning. More details can be found in Publications and Projects.
• I had some internship experiences, including Ant Group (Digital Finance, Jun. 2021) and Alibaba Group (Platform of AI, AIR intern, Sep. 2022).
• I like writing Chinese blogs at CSDN, sharing some papers and research knowledge of NLP, you can visit my Chinese blogs in here.
• If you have any comments, please click here to let me know!

News

• [2026-01-27] 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. 🔥🔥🔥
• [2026-01-23] We release EvoCUA, which focus on GUI agent and achieves SOTA performance (56.7%) through all open-weights models on OS-World leaderboard. 🔥🔥🔥
• [2026-01-15] We release LongCat-Flash-Thinking-2601, which aims at advancing our prior LongCat-Flash-Thinking on agentic tool use, searching and heavy thinking. 🔥🔥🔥
• [2025-09-22] We release LongCat-Flash-Thinking, which is an efficient and powerful large reasoning model on solving general reasoning, formal proving, and agentic tasks.
• [2025-08-21] Our two papers have been accepted to EMNLP 2025 (Findings and Main): Prejudge-Before-Think: A new Thinking Pattern for LLM, Analysis of Formal Language in LLM
• [2025-05-16] Our two papers have been accepted to ACL 2025 (Both are Main): Visual Modality Analysis, LogicPro
• [2025-01-23] Our one paper has been accepted to ICLR 2025: OCEAN: Offline CoT for RLVR
• [2024-12-10] Our one paper has been accepted to AAAI 2025: Uncertainty-Preference-Optimization
• [2024-05-19] Our two papers have been accepted to ACL 2024 (Main and Findings): Chain-of-Knowledge, InstructGraph
• [2024-03-25] Our new survey on neural code intelligent (NCI) has been released in ArXiv: A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond. 🔥🔥🔥
• [2024-03-14] Our one paper has been accepted to the Findings of NAACL 2024.
• [2024-02-13] Our InstructGraph (Graph + LLMs) has been released in GitHub. 🔥🔥🔥
• [2023-10-25] Our HugNLP has been awarded CIKM 2023 Best Demo Paper Award!
• [2023-10-20] I will visit Julian’s team at UCSD for about four months.
• [2023-10-08] Our 4 papers have been accepted to EMNLP 2023.
• [2023-08-06] The HugNLP has been accepted to CIKM 2023.
• [2023-05-05] The HugNLP has been released in https://github.com/HugAILab/HugNLP. 🔥🔥🔥
• [2023-04-13] Establish HugAILab.
• [2023-04-13] The homepage is opened!