Qing ZONG 宗晴

Qing ZONG 宗晴

Welcome to my homepage! :D 🥂

About me 👩‍🎓

I am a Ph.D. student in Computer Science and Engineering at the Hong Kong University of Science and Technology, supervised by Prof. Yangqiu Song. Before joining HKUST, I received my bachelor's degree in Computer Science and Technology from Harbin Institute of Technology (Shenzhen) in 2024.

Research Interest 💡

My research aims to build reliable, self-evolving agentic systems that can continue to improve or adapt to changing environments after deployment, beyond fixed human-designed paths. My current research interests include:

  • Co-evolution in Agentic Systems. I study how multiple evolving units, such as agents, environments, and even the evolution mechanism that governs their joint evolution, can adapt and reshape one another.
  • LLM Trustworthiness and Robustness. I study when model knowledge becomes unreliable and how language models can express better-calibrated confidence and uncertainty.

News 📣

  • Aug. 2026 7 papers were accepted to EMNLP 2026!
  • Jul. 2026 1 paper was accepted to COLM 2026!
  • Apr. 2026 4 papers were accepted to ACL 2026!
  • Jan. 2026 Started a research internship at Tencent Lightspeed Studios.
  • Dec. 2025 Received the Outstanding Reviewer Award at EMNLP 2025!
  • May 2025 2 papers were accepted to ACL 2025!

Publications 📝

You can also find my publications on my Google Scholar profile.

First-Author Publications

Self-Evolving Agents

  • Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

    Qing Zong, Jiayu Liu, Junhao Shen, Zecong Tang, Linsi Wu, Yuxuan Liu, Rui Wang, …, Yangqiu Song

    Under Review

  • EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

    Qing Zong, Yue Guo, Mengxin Yang, Yiwen Guo, Yangqiu Song

    EMNLP 2026

LLM Trustworthiness

  • CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

    Qing Zong, Jiayu Liu, Tianshi Zheng, Chunyang Li, Baixuan Xu, Haochen Shi, Weiqi Wang, …, Yangqiu Song

    Under Review

    [paper][code]

  • ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty

    Qing Zong, Zhaowei Wang, Tianshi Zheng, Xiyu Ren, Yangqiu Song

    ACL 2025

    [paper][code]

Multimodal Reasoning

  • TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining

    Qing Zong, Zhaowei Wang, Baixuan Xu, Tianshi Zheng, Haochen Shi, Weiqi Wang, Yangqiu Song, Ginny Y. Wong, Simon See

    The 10th Workshop on Argument Mining, 2023

    [paper][code]

Non-First-Author Publications

Self-Evolving Agents

  • Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds

    Yuxuan Liu, Zhaochen Su, Yuhao Zhang, Jiahe Guo, Zhongwei Xie, Huihao Jing, Lingyun Xie, Qing Zong, …, Yangqiu Song

    Under Review

    [paper]

  • SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

    Yuxuan Liu, Zhaochen Su, Lingyun Xie, Yuhao Zhang, Qing Zong, Jiahe Guo, Zhongwei Xie, …, Yangqiu Song

    EMNLP 2026

    [paper]

LLM Trustworthiness

  • NAACL: Noise-Aware Verbal Confidence Calibration for LLMs in RAG Systems

    Jiayu Liu, Rui Wang, Qing Zong, Qingcheng Zeng, Tianshi Zheng, Haochen Shi, Dadi Guo, …, Yangqiu Song

    EMNLP 2026

    [paper]

  • Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

    Rui Wang, Qihan Lin, Jiayu Liu, Qing Zong, Tianshi Zheng, Dadi Guo, Haochen Shi, …, Yangqiu Song

    EMNLP 2026

    [paper]

  • Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty?

    Jiayu Liu, Qing Zong, Weiqi Wang, Yangqiu Song

    ACL 2025

    [paper][code]

  • The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning

    Tianshi Zheng, Yixiang Chen, Chengxi Li, Chunyang Li, Qing Zong, …, Yangqiu Song, Ginny Y. Wong, Simon See

    TMLR 2025

    [paper][code]

Dynamic Reasoning & Adaptation

  • L²-Planbench: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

    Jiayu Liu, Qihan Lin, Cheng Qian, Rui Wang, Emre Can Acikgoz, Xiaocheng Yang, Qing Zong, …, Heng Ji, Dilek Hakkani-Tür

    EMNLP 2026

    [paper]

  • MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning

    Kawai Chung, Chunkit Chan, Yauwai Yim, Yuxuan Liu, Haochen Shi, Weiqi Wang, Qing Zong, …, Yangqiu Song

    EMNLP 2026

    [paper]

  • AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints

    Jiayu Liu, Cheng Qian, Zhenhailong Wang, Bingxuan Li, Jiateng Liu, Qing Zong, Heng Wang, …, Yi R. Fung, Heng Ji

    COLM 2026

  • CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

    Jiayu Liu, Cheng Qian, Zhaochen Su, Qing Zong, Shijue Huang, Bingxiang He, Yi R. Fung

    ACL 2026

    [paper][code]

  • SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding

    Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, …, Yangqiu Song

    ACL 2026

    [paper]

Structured Knowledge

  • AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora

    Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, …, Yangqiu Song

    ACL 2026

    [paper][code]

  • AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

    Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, …, Yangqiu Song, Ginny Y. Wong, Simon See

    ACL 2024

    [paper][code]

Multimodal Reasoning

  • Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos

    Baixuan Xu, Yinyui XU, Tianshi Zheng, Zhaowei Wang, Weiqi Wang, Haochen Shi, Wei Fan, Jiayu Liu, Qing Zong, …, Yangqiu Song

    EMNLP 2026

  • DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay

    Yunxiang Mo, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, …, Yangqiu Song

    ACL 2026

    [paper]

Experience 💼

Research Intern, Tencent Lightspeed Studios, Technology Development DepartmentJan 2026 – Present
  • Lead a project on co-evolving role-play agents and world models for interactive literary worlds, a frontier exploration for open-world game development. The resulting paper, EvolvingWorld, was accepted to EMNLP 2026.

Awards 🏆

Education 🎓

The Hong Kong University of Science and Technology2024 – Present

Ph.D. in Computer Science and Engineering; Advisor: Prof. Yangqiu Song

Harbin Institute of Technology (Shenzhen)2020 – 2024

Bachelor's Degree in Computer Science and Technology; Outstanding Graduate

Jiangsu Tianyi High School2017 – 2020

High School Diploma in Science

Contact me! ✉️

You can reach me at qzong@connect.ust.hk.