Preprint
Aug 2026
What Survives the Next Model? Benchmarking LLM-Based Techniques Against Single-Prompts
Analysis of technique papers from ICSE 2026 finds that a newer model with a single prompt natively outperforms the heavily engineered tooling proposed just a year prior, and identifies that constructive techniques like code generation or repair are more amenable to substitution by a single-prompt.
Nahian Salsabil, Joy Saha, S. Dristi et al.
· 0 citations