Changle Qu

Changle Qu

Ph.D. Candidate at Gaoling School of Artificial Intelligence, Renmin University of China, focusing on Tool Learning, Recommender System and Information Retrieval.

I am a third-year Ph.D. candidate at Intelligent Information Retrieval Lab (IIR Lab) from the Gaoling School of Artificial Intelligence (GSAI), Renmin University of China (RUC), supervised by Prof. Jun Xu. I obtained my bachelor’s degree from Huazhong University of Science and Technology (HUST) in June 2023. My research interests include Tool Learning with Large Language Models, Recommender System, and Information Retrieval.

🔥 News

  • 2026.04:  🎉🎉 My first-author paper ‘‘MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching’’is accepted by (ACL 2026)!
  • 2026.04:  🎉🎉 My first-author paper ‘‘KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation’’ and our paper ‘‘Learning to Retrieve from Agent Trajectories’’ are accepted by (SIGIR 2026)!
  • 2026.01:  🎉🎉 Our paper ‘‘Room matters: Dynamic room-level collaboration information modeling for live streaming recommendation’’ is accepted by (WWW 2026)!
  • 2025.08:  🎉🎉 My first-author paper ‘‘Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation’’ is accepted by (EMNLP 2025 Findings)!
  • 2025.05:  🎉🎉 Our paper ‘‘Retrieving Intent-covering Demonstrations for Clarification Generation in Conversational Search Systems’’ is accepted by (KDD 2025)!
  • 2025.04:  🎉🎉 My first-author paper ‘‘Bridging Short Videos and Streamers with Multi-Graph Contrastive Learning for Live Streaming Recommendation’’ is accepted by (SIGIR 2025)!
  • 2025.02:  🎉🎉 My first-author paper ‘‘From exploration to mastery: enabling LLMs to master tools via self-driven interactions’’ is selected as an Oral presentation (1.8%) at ICLR 2025!
  • 2025.01:  🎉🎉 My first-author paper ‘‘From exploration to mastery: enabling LLMs to master tools via self-driven interactions’’ is accepted by (ICLR 2025)!
  • 2024.09:  🎉🎉 My first-author paper ‘‘Tool learning with large language models: A survey’’ is accepted by (FCS)!
  • 2024.07:  🎉🎉 My first-author paper ‘‘Towards completeness-oriented tool retrieval for large language models’’ is accepted by (CIKM 2024)!
  • 2024.07:  🎉🎉 Our short paper ‘‘ReCODE: Modeling Repeat Consumption with Neural ODE’’ is honored as a Best Short Paper Nominee at SIGIR 2024!
  • 2024.03:  🎉🎉 Our paper ‘‘ReCODE: Modeling Repeat Consumption with Neural ODE’’ is accepted by (SIGIR 2024)!

📝 Publications

  • MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching

    Changle Qu, Sunhao Dai, Hengyi Cai, Jun Xu, Shuaiqiang Wang, Dawei Yin

    ACL 2026 | Paper

  • KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation

    Changle Qu, Sunhao Dai, Ke Guo, Xiao Zhang, Liqin Zhao, Shijun Wang, Yannan Niu, Lantao Hu, Han Li, Jun Xu

    SIGIR 2026 | Paper

  • Bridging Short Videos and Streamers with Multi-Graph Contrastive Learning for Live Streaming Recommendation

    Changle Qu, Liqin Zhao, Yannan Niu, Xiao Zhang, Jun Xu

    SIGIR 2025 | Paper

  • From exploration to mastery: enabling LLMs to master tools via self-driven interactions

    Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen

    ICLR 2025 | Oral (1.8%) | Paper

  • Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation

    Changle Qu, Sunhao Dai, Hengyi Cai, Yiyang Cheng, Jun Xu, Shuaiqiang Wang, Dawei Yin

    EMNLP 2025 Findings | Paper

  • Tool learning with large language models: A survey

    Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen

    FCS | Paper | GitHub Repo stars

  • Towards completeness-oriented tool retrieval for large language models

    Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen

    CIKM 2024 | Paper

  • Towards ai search paradigm

    Baidu Search Team (23 authors including Changle Qu).

    Technical Report | Paper

  • Learning to Retrieve from Agent Trajectories

    Yuqi Zhou, Sunhao Dai, Changle Qu, Liang Pang, Jun Xu, Ji-Rong Wen.

    SIGIR 2026 | Paper

  • Room matters: Dynamic room-level collaboration information modeling for live streaming recommendation

    Ke Guo, Changle Qu, Xiao Zhang, Liqin Zhao, Shijun Wang, Yanan Niu, Jun Xu.

    WWW 2026 | Paper

  • Retrieving Intent-covering Demonstrations for Clarification Generation in Conversational Search Systems

    Ziliang Zhao, Changle Qu, Zhicheng Dou, Haonan Chen, Jiajie Jin

    KDD 2025 | Paper

  • ReCODE: Modeling Repeat Consumption with Neural ODE

    Sunhao Dai, Changle Qu, Sirui Chen, Xiao Zhang, Jun Xu

    SIGIR 2024 Short Paper | Best Short Paper Nominee | Paper

🎖 Honors and Awards

  • 2025.02 ICLR 2025 Oral presentation (1.8%).
  • 2024.07 SIGIR 2024 Best Short Paper Nominees.
  • 2022.10 Merit Student Scholarship in Huazhong University of Science and Technology.
  • 2022.05 Finalist Winners (Top 2%) at American Undergraduate Mathematical Contest in Modeling.

📖 Educations

  • 2023.09 - Present, PhD Candidate. Gaoling School of Artificial Intelligence, Renmin University of China.
  • 2019.09 - 2023.06, Bachelor in Cyberspace Security. School of Cyberspace Security, Huazhong University of Science and Technology.

📚 Academic Services

  • Program Committee / Reviewer: SIGIR 2025-2026, SIGIR-AP 2025, WSDM 2026, KDD 2026
  • Secondary Reviewer: ACL 2024-2026, EMNLP 2024-2025, ICLR 2025, ICML 2025-2026, NeurIPS 2025

👩🏻‍🏫 Teaching

  • Teaching Assistant, Introduction to Big Data Analytics, Renmin University of China, Fall 2025
  • Teaching Assistant, Freshman Seminar on Information Retrieval, Renmin University of China, Spring 2025
  • Teaching Assistant, Introduction to Big Data Analytics, Renmin University of China, Fall 2024

💻 Internships

  • Baidu Inc., Search Strategy Department, focusing on tool learning with llms.
  • Kuaishou Technology, Live Streaming Recommendation Department, focusing on live streaming recommendation.