REPOCOD
PulseAugur coverage of REPOCOD — every cluster mentioning REPOCOD across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New REPOCOD benchmark reveals LLMs struggle with real-world coding tasks
A new benchmark called REPOCOD has been developed to evaluate the capabilities of large language models (LLMs) in real-world coding tasks. Existing benchmarks like CoderEval and HumanEval are criticized for focusing on …
-
AI agent ProjAgent improves code retrieval; TokenWall cuts agent attack rate
ProjAgent has achieved a 41.14% Pass@1 score on the REPOCOD benchmark by implementing a novel procedural code retrieval method. This new signal helps the agent identify code that performs similar functions but uses diff…
-
New research tackles AI code generation evaluation and testing
Two new research papers explore advancements in evaluating AI-generated code. The first, TENET, introduces a framework for repository-level code generation using test-driven development, achieving high Pass@1 scores on …
-
ProjAgent system enhances code generation with procedural similarity retrieval
Researchers have developed ProjAgent, a novel system for repository-level code generation that introduces procedural similarity as a key retrieval signal. Unlike existing methods that rely on lexical or structural simil…