AnnCoder: A mti-Agent-Based Code Generation and Optimization Model

Abstract excerpt

The rapid progress of LLMs has greatly improved natural language tasks like code generation, boosting developer productivity. However, challenges persist. Generated code often appears "pseudo-correct"—passing functional tests but plagued by inefficiency or redundant structures. Many models rely on outdated methods like greedy selection, which trap them in local optima, limiting their ability to explore b...

Topics

Open a Topic to create a Post that cites this publication.

• Carboplatin
• Cyclophosphamide
• Etoposide
• Genetics, Bioinformatics, and Biomedical Research
• Human T-lymphotropic virus 1
• Leukemia-Lymphoma, Adult T-Cell
• Prednisolone
• Receptors, Cytokine

Identifiers and source

Literature Corpus work

4e3fb948-41fc-5310-a3ca-391687dd1a6c

DOI

10.20944/preprints202505.2257.v1