New paper: Model-Based Recursive Self-Improvement with ARC-AGI results released
hbouammar · x · 2026-10-09
Author hbouammar announced the release of the paper "Model-Based Recursive Self-Improvement," highlighting its ARC-AGI benchmark results. The tweet itself is thin; details are in the paper itself.
More from Research
- Researcher finds many eval harness functions exist only to patch dataset flaws — remilouf · 2026-10-11
- Bo Wang joins SF Tech Week 'Models to Medicine' panel on virtual cells and Xaira — BoWang87 · 2026-10-11
- AI on track to solve 1,000+ math problems in a month, a 100x jump in 2 months — Dr_Singularity · 2026-10-11
- "The product of math is proofs": a case for vibe mathing everything with AI — cgarciae88 · 2026-10-11
- OpenAI drops 372 math proofs, and mathematicians are grieving — genmon · 2026-10-11
- Was Claude's gibberish fixed by capping KL divergence in RL? One theory — burny_tech · 2026-10-11