publications

2026

1. AutoSWE

   Towards Autonomous Software Engineering

   Wang, Hao, Meng, Ruijie, Ye, Zhe, Gu, Alex, Jain, Naman, Liu, Xiaoyuan, Chaudhuri, Swarat, Zimmermann, Thomas, Gulwani, Sumit, Solar-Lezama, Armando, Stoica, Ion, and Song, Dawn

   2026

   PDF
2. RECEIPT

   RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery

   Lyu, Muxi, Shieh, Karen, Hou, Yiwei,  Wang, Hao, Sen, Koushik, and Wagner, David

   2026

   ArXiv
3. ConfFuzz

   ConfFuzz: Parameter-Aware Greybox Fuzzing for Configurable Cloud Systems

   Wang, Shuai,  Wang, Hao, Marinov, Darko, Xu, Tianyin, and Zhang, Yongle

   In ASE 2026
4. BenchJack

   Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack

   Wang, Hao, Li, Hanchen, Mang, Qiuyang, Cheung, Alvin, Sen, Koushik, and Song, Dawn

   2026

   ArXiv 𝕏
5. Revelio

   Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases

   Hou, Yiwei,  Wang, Hao, Lyu, Muxi, Momeu, Marius, Nguyen, Eric, Yang, Taige, Sen, Koushik, Song, Dawn, and Wagner, David

   2026

   ArXiv
6. SecPI

   SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization

   Wang, Hao, Mündler, Niels, Vero, Mark, He, Jingxuan, Song, Dawn, and Vechev, Martin

   2026

   ArXiv

2025

1. Climbing the Ladder of Reasoning: What LLMs Can-and Still Can’t-Solve after SFT?

   Sun, Yiyou, Zhou, Georgia, Bai, Haoyue,  Wang, Hao, Li, Dacheng, Dziri, Nouha, and Song, Dawn

   In MATH-AI Workshop @ NeurIPS (Poster) 2025

   ArXiv
2. SCGAgent

   SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

   Saul, Rebecca,  Wang, Hao, Sen, Koushik, and Wagner, David

   2025

   ArXiv
3. Type

   Type-Constrained Code Generation with Language Models

   Mündler, Niels, He, Jingxuan,  Wang, Hao, Sen, Koushik, Song, Dawn, and Vechev, Martin

   In PLDI 2025

   ArXiv
4. QLangevin

   Quantum Langevin Dynamics for Optimization

   Chen, Zherui, Lu, Yuchen,  Wang, Hao, Liu, Yizhou, and Li, Tongyang

   Communications in Mathematical Physics 2025

   ArXiv

2024

1. Sail

   Skill-Adaptive Imitation Learning for UI Test Reuse

   Wu, Mengzhou,  Wang, Hao, Ren, Jun, Cao, Yuan, Li, Yuetong, Jiang, Alex, Ran, Dezhi, Hu, Yitao, Yang, Wei, and Xie, Tao

   2024

   ArXiv
2. HA RTP

   Hierarchy-Aware Regression Test Prioritization

   Wang, Hao, Yi, Pu, Parladorio, Jeremias, Lam, Wing, Marinov, Darko, and Xie, Tao

   In ISSRE 2024

   PDF
3. Guardian

   Guardian: A Runtime Framework for LLM-based UI Exploration

   Ran, Dezhi,  Wang, Hao, Song, Zihe, Wu, Mengzhou, Cao, Yuan, Zhang, Ying, Yang, Wei, and Xie, Tao

   In ISSTA 2024

   PDF
4. Quantum

   Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss

   Wang, Hao, Zhang, Chenyi, and Li, Tongyang

   In The Twelfth International Conference on Learning Representations 2024

   ArXiv Bib

   @inproceedings{wang2024nearoptimal,
     title = {Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss},
     author = {Wang, Hao and Zhang, Chenyi and Li, Tongyang},
     booktitle = {The Twelfth International Conference on Learning Representations},
     year = {2024},
     url = {https://openreview.net/forum?id=pB1FeRSQxh}
   }

2023

1. BADGE

   BADGE: Prioritizing UI Events with Hierarchical Multi-Armed Bandits for Automated UI Testing

   Ran, Dezhi,  Wang, Hao, Wang, Wenyu, and Xie, Tao

   In ICSE 2023

   Bib PDF

   @inproceedings{dezhi2023android,
     booktitle = {ICSE},
     author = {Ran, Dezhi and Wang, Hao and Wang, Wenyu and Xie, Tao},
     title = {BADGE: Prioritizing UI Events with Hierarchical Multi-Armed Bandits for Automated UI Testing},
     year = {2023},
   }

2022

1. Random RTP

   A Theoretical Analysis of Random Regression Test Prioritization

   Yi, Pu,  Wang, Hao, Xie, Tao, Marinov, Darko, and Lam, Wing

   In TACAS 2022

   Abs Bib PDF

   Regression testing is an important activity to check software changes by running the tests in a test suite to inform the developers whether the changes lead to test failures. Regression test prioritization (RTP) aims to inform the developers faster by ordering the test suite so that tests likely to fail are run earlier. Many RTP techniques have been proposed and are often compared with the random RTP baseline by sampling some of the n! different test-suite orders for a test suite with n tests. However, there is no theoretical analysis of random RTP. We present such an analysis, deriving probability mass functions and expected values for metrics and scenarios commonly used in RTP research. Using our analysis, we revisit some of the most highly cited RTP papers and find that some presented results may be due to insufficient sampling. Future RTP research can leverage our analysis and need not use random sampling but can use our simple formulas or algorithms to more precisely compare with random RTP.

   @inproceedings{pu2022randomrtp,
     author = {Yi, Pu and Wang, Hao and Xie, Tao and Marinov, Darko and Lam, Wing},
     editor = {Fisman, Dana and Rosu, Grigore},
     title = {A Theoretical Analysis of Random Regression Test Prioritization},
     booktitle = {TACAS},
     year = {2022},
     publisher = {Springer International Publishing},
     address = {Cham},
     pages = {217--235},
     isbn = {978-3-030-99527-0}
   }