Metraipolis › archive › dc_fa3aed147997

From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning — arXiv:2609.38402

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38402
License (as archived): CC0-1.0
Archived: 2026-10-07T13:47:11.446Z
SHA-256 of the archived text: 436f6a1ec49ddd36b0393f6bb9208b79a365028744f18acbc3aaba6f603ec818
Stable URL of this page: https://metraipolis.com/documento/dc_fa3aed147997

How to cite

From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning — arXiv:2609.38402 — arXiv (en), https://arxiv.org/abs/2609.38402 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa3aed147997 (Metraipolis archive dc_fa3aed147997, sha256 436f6a1ec49ddd36b0393f6bb9208b79a365028744f18acbc3aaba6f603ec818)

BibTeX

@misc{dcfa3aed147997,
  title = {From Codebase to Culprit (C2C): Reducing the Search Space for Bugs with Semantic Retrieval and Hierarchical Reinforcement Learning — arXiv:2609.38402},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38402},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa3aed147997; sha256 436f6a1ec49ddd36b0393f6bb9208b79a365028744f18acbc3aaba6f603ec818},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38402. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce C2C (From Codebase to Culprit), a framework for precise bug localization that progressively reduces the debugging search space across multiple levels of granularity: files, functions, and lines of code. To mirror developer's natural top-down debugging workflows, C2C integrates semantic retrieval and Hierarchical Reinforcement Learning (HRL) in a two-stage process. First, it performs recall-oriented retrieval of buggy candidates via semantic vector similarity search using bug-report text, including available stack-trace information, against a database of embeddings, where the embeddings are fine-tuned via contrastive learning with CodeBERT. Building on this reduced search space, the HRL framework incrementally localizes bugs, reasoning from files to functions and ultimately to individual lines of code. Unlike prior approaches which operate at a single granularity, C2C enables multi-resolution localization while maintaining contextual consistency across decisions. Experiments on real-world Java and Python datasets demonstrate that C2C improves retrieval precision and localization accuracy. Ablation studies further highlight the contributions of hierarchical decomposition, structured learning signals, and reward shaping in advancing multi-level bug localization.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Software Engineering (cs.SE) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.38402 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T13:18:10.560Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).