About Me

I am a master's student in Artificial Intelligence at Zhejiang University, expected to graduate in June 2027. I am a member of the Interactive Data Group (IDG) at the State Key Laboratory of CAD&CG, where I am jointly advised by Prof. Yingcai Wu and Prof. Di Weng.

My research lies at the intersection of natural language processing, human-computer interaction, and data intelligence. I build learning agents that improve through interaction, use tools over long horizons, and remain grounded in the data and context surrounding their decisions.

Recently, I have focused on agentic reinforcement learning, self-improving systems, and human–AI collaboration, with particular interest in fine-grained credit assignment, long-term coherence, and interactive systems that make model behavior easier to inspect and refine.

News

Three papers: SPADER, BIRD-History, and Modality Fault Lines were accepted to EMNLP 2026.
Papers coming soon for BIRD-History and Modality Fault Lines.

One of our pull requests was merged into Hermes.

MerchantBench ranked 🏆 #1 Paper of the Day on Hugging Face Daily Papers.

Joined Alibaba's 1688 team to work on self-improving agents and long-horizon RL.

Selected Publications

* Equal contribution; † Corresponding author

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Qiming Shi, Yulong Tao, Linbo Jin, Zhaolu Kang, Yibo Dou, Jiawen Zhu, Tianjun Pan, Shaokang Fu, Chengyu Wang, Siyue Li, Yaping Cheng, Di Weng, Chengfu Huo

TopicsLong-HorizonBenchmark

SKILL-KD: Contrastive Skill Distillation for LLM Agents

Qiming Shi, Yibo Dou, Jiawen Zhu, Yulong Tao, Linbo Jin, Zhaolu Kang, Yunfan Zhou, Di Weng

arXiv 2026
TopicsSelf-ImprovingSkills

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

Qiming Shi*, Zhaolu Kang*, Yunfan Zhou, Di Weng, Yingcai Wu

EMNLP 2026CORE A*
TopicsAgentic RLSearch Agent

Cerebra: Aligning Implicit Knowledge in Interactive SQL Authoring

Yunfan Zhou, Qiming Shi, Zhongsu Luo, Xiwen Cai, Yanwei Huang, Dae Hyun Kim, Di Weng, Yingcai Wu

CHI 2026CCF-A
TopicsCode LLMHCI

Xavier: Toward Better Coding Assistance in Authoring Tabular Data Wrangling Scripts

Yunfan Zhou, Xiwen Cai, Qiming Shi, Yanwei Huang, Haotian Li, Huamin Qu, Di Weng, Yingcai Wu

CHI 2025CCF-A
TopicsCode LLMHCI