LogicLoc combines LLMs with Datalog to achieve accurate repo-level code localization without relying on keyword shortcuts in benchmarks.
Coderepoqa: A large-scale benchmark for software engineering question answering,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
The paper presents a vision for an agentic code review framework spanning PR Creation, Augmentation, Reviewer Selection, AI-Assisted Review, and Retrospective, with humans retained at quality gates.
citing papers explorer
-
Neurosymbolic Repo-level Code Localization
LogicLoc combines LLMs with Datalog to achieve accurate repo-level code localization without relying on keyword shortcuts in benchmarks.
-
SWE-QA: Can Language Models Answer Repository-level Code Questions?
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
-
Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review
The paper presents a vision for an agentic code review framework spanning PR Creation, Augmentation, Reviewer Selection, AI-Assisted Review, and Retrospective, with humans retained at quality gates.