Prompt Repetition Experiments
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
28 agent sessions (4,179 messages) testing whether prompt repetition improves AI coding agent accuracy. Two pre-registered experiments showing a ceiling-accuracy null result on structured engineering tasks.
Fields of Study & Subjects
Software Engineering Research
Software Engineering Techniques and Practices
Artificial Intelligence Applications
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 23 February 2026
- Language
- EN
- Document type
- Dataset