Yuling Shi

🙋 About Me

Hi, I am a fourth year Ph.D. student in the LLM for Software Engineering Lab (LLMSE), affiliated with the School of Software at Shanghai Jiao Tong University in China. I’m grateful to be advised by Prof. Xiaodong Gu and Prof. Beijun Shen.

Some of my recent projects can be found in my Github homepage here. Feel free to contact me if you are interested in my work or have any questions.

🧐 Research Interests

• Software Engineering: code generation, code debugging, software issue resolution, code question answering
• Natural Language Processing: post training, retrieval augmented generation, multi-agent systems

📰 News

• [2026.02] Received ACM SIGSOFT ICSE 2026 CAPS Grant (Travel Support)
• [2026.01] Serving as PC member of AIware 2026; submissions are welcome
• [2026.01] Awarded Shanghai Association for Artificial Intelligence Youth Outstanding Paper Award
• [2026.01] Two papers accepted by ICLR 2026
• [2026.01] One paper accepted by WWW 2026 GLOW Workshop
• [2025.11] Invited talk at Ant Group: “How to understand and debug large and complex programs?”
• [2025.11] Invited talk at CCF Synonym: “Hierarchical debugging with LLMs.”
• [2025.11] Invited talk at CCF Synonym: “How to compress long code context?”
• [2025.12] Won 9th place in Shanghai University Table Tennis Men’s Singles Championship
• [2025.12] One paper accepted by FSE 2026
• [2025.12] Three papers accepted by AAMAS 2026
• [2025.10] Invited talk at ByteDance Software Engineering Lab: “Dealing with long context problem in SE.”
• [2025.12] One paper accepted by ICSE 2026 SEIP track
• [2025.12] Two papers accepted by ICSE 2026
• [2025.10] One paper accepted by ICSE 2026
• [2025.10] One paper accepted by ASE 2025
• [2025.08] One paper accepted by EMNLP 2025 Findings
• [2025.05] One paper accepted by ACL 2025 KnowFM Workshop
• [2024.10] Invited talk at Tongyi Lab, Alibaba: “Hierarchical debugging with LLMs.”
• [2024.08] Invited talk at CCF Synonym: “How to detect LLM generated code?”
• [2024.07] One paper accepted by ICSE 2025

📝 Publications

† denotes equal contribution.

Publications

• Robust Preference Alignment via Directional Neighborhood Consensus
  ICLR 2026
  Ruochen Mao, Yuling Shi, Xiaodong Gu, Jiaheng Wei

• Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
  ICLR 2026
  Runze Liu, Jiakang Wang, Yuling Shi, Zhihui Xie, Chenxin An, Kaiyan Zhang, Jian Zhao, Xiaodong Gu, Lei Lin, Wenping Hu, Xiu Li, Fuzheng Zhang, Guorui Zhou, Kun Gai

• In Line with Context: Repository-Level Code Generation via Context Inlining
  FSE 2026
  Chao Hu, Wenhao Zeng, Yuling Shi, Beijun Shen, Xiaodong Gu

• From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
  ICSE 2026
  Yuling Shi, Songsong Wang, Chengcheng Wan, Min Wang, Xiaodong Gu

• SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
  ICSE 2026
  Han Li†, Yuling Shi†, Shaoxin Lin, Xiaodong Gu, Heng Lian, Xin Wang, Yantao Jia, Tao Huang, Qianxiang Wang

• EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation
  ICSE 2026 SEIP
  Chaofan Wang, Tingrui Yu, Chen Xie, Jie Wang, Dong Chen, Wenrui Zhang, Yuling Shi, Xiaodong Gu, Beijun Shen

• HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
  AAMAS 2026
  Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang

• GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
  AAMAS 2026
  Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang

• D³MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
  AAMAS 2026
  Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang

• Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  WWW 2026 GLOW
  Yuling Shi, Maolin Sun, Zijun Liu, Mo Yang, Yixiong Fang, Tianran Sun, Xiaodong Gu

• LongCodeZip: Compress Long Context for Code Language Models
  ASE 2025
  Yuling Shi, Yichun Qian, Hongyu Zhang, Beijun Shen, Xiaodong Gu

• Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers
  ICSE 2025
  Yuling Shi, Hongyu Zhang, Chengcheng Wan, Xiaodong Gu

• LastingBench: Defend Benchmarks Against Knowledge Leakage
  EMNLP 2025 Findings
  Yixiong Fang, Tianran Sun, Yuling Shi, Min Wang, Xiaodong Gu

• AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
  ACL 2025 KnowFM
  Yixiong Fang, Tianran Sun, Yuling Shi, Xiaodong Gu

• A Morley-Wang-Xu element method for a fourth order elliptic singular perturbation problem
  Journal of Scientific Computing (Q1), 2021
  Xuehai Huang, Yuling Shi and Wenqing Wang

Preprints

• CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
  Preprint
  Yuling Shi, Chaoxiang Xie, Zhensu Sun, Yeheng Chen, Chenxu Zhang, Longfei Yun, Chengcheng Wan, Hongyu Zhang, David Lo, Xiaodong Gu

• SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
  Preprint
  Yuhang Wang†, Yuling Shi†, Mo Yang, Rongrui Zhang, Shilin He, Heng Lian, Yuting Chen, Siyu Ye, Kai Cai, Xiaodong Gu

• GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
  Preprint
  Wenhao Zeng, Xuteng Zhang, Yuling Shi, Chao Hu, Yuting Chen, Beijun Shen, Xiaodong Gu

• Progressive Supernet Training for Efficient Visual Autoregressive Modeling
  Preprint
  Xiaoyue Chen†, Yuling Shi†, Kaiyuan Li†, Huandong Wang, Yong Li, Xiaodong Gu, Xinlei Chen, Mingbao Lin

• SWE-Exp: Experience-Driven Software Issue Resolution
  Preprint
  Silin Chen, Shaoxin Lin, Yuling Shi, Heng Lian, Xiaodong Gu, Longfei Yun, Dong Chen, Lin Cao, Jiyang Liu, Nu Xia, Qianxiang Wang

• Repository-level Code Question Answering
  Preprint
  Weihan Peng, Yuling Shi, Yuhang Wang, Xinyun Zhang, Beijun Shen, Xiaodong Gu

• Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents
  Preprint
  Xiang Chen, Yuling Shi, Qizhen Lan, Yuchao Qiu, Min Wang, Xiaodong Gu, Yanfu Yan

• Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal
  Preprint
  Wenhao Zeng, Yaoning Wang, Chao Hu, Yuling Shi, Chengcheng Wan, Hongyu Zhang, Xiaodong Gu

👨‍💻 Experiences

• Research Intern at Microsoft Research, 2022.03-2022.09
  • Grateful to be advised by Dr. Yufan Huang and Dr. Maoquan Wang to work on analyzing neural representations of code. Some of my work contributed to the following paper on EMNLP 2023. [pdf]

📣 Invited Talks

• How to understand and debug large and complex programs? at Ant Group, November 2025
• Hierarchical debugging with LLMs. at CCF Synonym, November 2025
• How to compress long code context? at CCF Synonym, November 2025
• Dealing with long context problem in SE. at Software Engineering Lab, ByteDance, October 2025
• Hierarchical debugging with LLMs. at Tongyi Lab, Alibaba, October 2024
• How to detect LLM generated code? at CCF Synonym, August 2024

📚 Teaching

• Teaching Assistant for “Machine Learning” (Fall 2022, Fall 2023, Spring 2024, Spring 2025)
• Teaching Assistant for “Math for Machine Learning” (Spring 2024)
• Teaching Assistant for FL4207 “Application of LLMs” (Fall 2025)

💼 Services

• Conference Reviewer: ICLR 2025, ARR Oct 2025, ICLR 2026, ICSE 2026 (Shadow PC), CVPR 2026, ICML 2026, AIware 2026
• Journal Reviewer: TMLR

🏆 Awards

• 🏆 ACM SIGSOFT ICSE 2026 CAPS Travel Grant
• 🥇 Shanghai Association for Artificial Intelligence Youth Outstanding Paper Award
• 🏆 National Scholarship
• 🏓 Fifth place in Shanghai Table Tennis Doubles Championship and third place in teams representing my university
• 🏆 First Prize in National Olympiad in Physics at High school (Provincial Area)

📖 Materials to share

• 🔥 A collection of resources for repo-level code generation. [Github]
• A simple script to detect word by word plagiarism for Academic Writing course in SJTU. [Github]

Thank you for visiting my homepage!

The truth is lived, not taught. -Hermann Hesse