35B Frontis-MA1 Beats GPT-5.5 via Evolutionary Recursive Self-Improvement
cwolferesearch · x · 2026-08-03
While most recursive self-improvement (RSI) research relies on coding agents for simple hill climbing, the Frontis-MA1 (35B) model introduces evolutionary/genetic algorithms to unlock greater potential.
Trained as a meta-evolution agent for machine learning engineering (MLE), the model features four atomic operators: Draft, Improve, Debug, and Crossover. Instead of generating a single pipeline, it evolves numerous code candidates in a sandbox, learning from real task scores to guide long-horizon search.
On MLE-Bench Lite (constrained to a single RTX 4090), the system boosts the base model's Medal Average from 39.39% to 60.61%. With experience priors and asynchronous search (Evo-Max), it reaches 71.21%, surpassing GPT-5.5 + Codex and approaching GPT-5.6 Sol and the 2.8T Kimi K3.
More from coding & agent
- Warp Ships Prompt Queueing for AI Coding Agents — vikvang1 · 2026-08-03
- Pi Coding Agent Integrates Celesto for Secure Cloud Execution — aniketmaurya · 2026-08-03
- Adam Jacob: AI Agents Will Spawn a New Category of 'Adaptive Software' — matt_slotnick · 2026-08-03
- Stop obsessing over one-shot prompts: conversation is key to AI game design — TAbrodi · 2026-08-03
- Commanding AI Coding Agents Makes Software Development Feel Like Starcraft — round · 2026-08-03
- Claude Skills in Action: Auto-Loading Custom Instructions to Optimize Context — anselm · 2026-08-03