Skip to content
AI News HubLIVE
More
Summary only

Recursive Self-Improvement Delivers New SOTA Coding Performance

Poetiq's Meta-System achieves state-of-the-art results on the LiveCodeBench Pro coding benchmark by automatically creating optimized harnesses via recursive self-improvement, without fine-tuning or special model access, boosting performance across multiple models.

SourceHacker News AIAuthor: icodestuff
Recursive Self-Improvement Delivers New SOTA Coding Performance
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Poetiq's Meta-System achieved 93.9% on LiveCodeBench Pro using GPT 5.5, surpassing previous SOTA.
  • The harness, built via recursive self-improvement, improves all tested models without model-specific fine-tuning.
  • Results include a 12.3% improvement for Gemini 3.1 Pro and a 30% improvement for Kimi K2.6.

Highlights and analysis are generated automatically and may contain errors. Check the original source.