Number of papers: 1
- Authors: Cummins, Chris and Seeker, Volker and Armengol-Estap{'e}, Jordi and Markosyan, Aram H and Synnaeve, Gabriel and Leather, Hugh
- Abstract: Tools for rewriting, refactoring and optimizing code should be fast and correct. Large language models (LLMs), by their nature, possess neither of these qualities. Yet, there remains tremendous opportunity in using LLMs to improve code. We explore the use of LLMs not to transform code, but to code transforms. We propose a chain-of-thought approach to synthesizing code transformations from a small number of input/output code examples that incorporates execution and feedback. Unlike the direct rew...
- Link: Read Paper
- Labels: agent design, prompt strategy, reason with code