Selected Publications

Full list see my Google Scholar

I have released the code in my Github Github. Feel free to check it out and chat with me if you have any questions.

2025

  1. Iterative Self-incentivization Empowers Large Language Models as Agentic Searchers
    Zhengliang Shi, Lingyong Yan, Dawei Yin, Suzan Verberne, Maarten Rijke, and Zhaochun Ren
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
    Paper Code GitHub Repo stars
  2. Deep Research: A Systematic Survey
    Zhengliang Shi, Yiqun Chen, Haitao Li, (20 authors), Yue Zhang, Yiming Yang, Zhaopeng Tu, and Zhaochun Ren
    arXiv preprint arXiv:202511.2077, 2025
    Paper Website Hugging Face Code GitHub Repo stars
  3. Tool learning in the wild: Empowering language models as automatic tool agents
    Zhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng, Xiuyi Chen, Zhumin Chen, Dawei Yin, Suzan Verberne, and Zhaochun Ren
    In Proceedings of the ACM on Web Conference 2025 (WWW), 2025
    Paper Website Hugging Face Code GitHub Repo stars
  4. Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
    Zhengliang Shi, Yuhan Wang, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Dawei Yin, and Zhaochun Ren
    In Proceedings of the 63nd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
    Paper Website Hugging Face Code GitHub Repo stars
  5. Direct retrieval-augmented optimization: Synergizing knowledge selection and language models
    Zhengliang Shi, Lingyong Yan, Weiwei Sun, Yue Feng, Pengjie Ren, Xinyu Ma, Shuaiqiang Wang, Dawei Yin, Maarten Rijke, and Zhaochun Ren
    arXiv preprint arXiv:2505.03075, 2025
    Paper Code GitHub Repo stars
  6. Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
    Dongsheng Zhu, Weixian Shi, Zhengliang Shi, Zhaochun Ren, Shuaiqiang Wang, Lingyong Yan, and Dawei Yin
    In Proceedings of the 63rd Annual Meeting of the Association for Computational (ACL), 2025
    Paper Website

2024

  1. Confucius: Iterative tool learning from introspection feedback by easy-to-difficult curriculum
    Zhengliang Shi, Shen Gao, Minghang Zhu, Bowen Fang, Xin Xin, Pengjie Ren, Zhumin Chen, Jun Ma, and Zhaochun Ren
    In Proceedings of the AAAI conference on artificial intelligence (AAAI), 2024
    Paper Code GitHub Repo stars
  2. Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
    Zhengliang Shi, Shuo Zhang, Weiwei Sun, Shen Gao, Pengjie Ren, Zhumin Chen, and Zhaochun Ren
    In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024
    Paper
  3. Learning to Use Tools via Cooperative and Interactive Agents
    Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, and Zhaochun Ren
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
    Paper Code GitHub Repo stars

2023

  1. Contrastive learning reduces hallucination in conversations
    Weiwei Sun, Zhengliang Shi, Shen Gao, Pengjie Ren, Maarten Rijke, and Zhaochun Ren
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2023
    Code GitHub Repo stars