Skip to content
AI News HubLIVE
Summary only

Poetiq’s Meta-System Automatically Builds a Model-Agnostic Harness That Improved Every LLM Tested on LiveCodeBench Pro Without Fine-Tuning

Poetiq's Meta-System automatically constructed and optimized an inference harness for LiveCodeBench Pro using only Gemini 3.1 Pro — no fine-tuning, no model internals. The same harness, applied without modification to GPT 5.5 High, Kimi K2.6, Gemini 3.0 Flash, and four other models, improved every one of them.

SourceMarkTechPostAuthor: Asif Razzaq
Poetiq’s Meta-System Automatically Builds a Model-Agnostic Harness That Improved Every LLM Tested on LiveCodeBench Pro Without Fine-Tuning
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 automatically builds task-specific harnesses through recursive self-improvement without fine-tuning or internal model access.
  • GPT 5.5 High with the harness scores 93.9% on LCB Pro (25Q2), up from 89.6%; Gemini 3.1 Pro jumps from 78.6% to 90.9%.
  • The harness is model-agnostic: optimized using only Gemini 3.1 Pro, it improved every other model tested, both open-weights and proprietary.
  • Smaller models like Gemini 3.0 Flash gain 10 percentage points (72.3% → 82.3%), surpassing much larger and expensive models.

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

More recent stories on this topic · Models