@inproceedings{yang-etal-2026-securepair,
    title = "{S}e{C}u{R}epair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework",
    author = "Yang, Chengran  and
      Zhang, Ting  and
      Jiang, Jinfeng  and
      Zhou, Xin  and
      Tian, Haoye  and
      Du, Mingzhe  and
      Shi, Jieke  and
      Chen, Junkai  and
      Li, Yikun  and
      Ouh, Eng Lieh  and
      Shar, Lwin Khin  and
      Lo, David",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1481/",
    pages = "32108--32123",
    ISBN = "979-8-89176-390-6",
    abstract = "The rapid accumulation of software vulnerabilities has outpaced manual remediation, creating an urgent need for Automated Vulnerability Repair (AVR). However, existing methods suffer from syntactic overfitting, mimicking surface forms without understanding the underlying repair logic, and fail to generalize to complex fixes. To transcend these limitations, we propose SeCuRepair, a reliable, scalable, and efficient RL-based AVR framework. By introducing a semantic-aware reward, SeCuRepair optimizes for code semantic equivalence rather than lexical mimicry. Furthermore, SeCuRepair incorporates an expert-aligned reasoning mechanism that explicitly grounds patch generation in a structured diagnosis. Finally, SeCuRepair introduces a difficulty-based curriculum that progressively disentangles the optimization barriers of entangled multi-hunk repairs. Extensive evaluations on a rigorous repository-level split show that SeCuRepair substantially outperforms state-of-the-art baselines, as confirmed by both automatic evaluation and human study."
}