RSI-Exam Benchmark Launches to Test AI Recursive Self-Improvement
HuaxiuYaoML · x · 2026-08-27
RSI-Exam, a new benchmark with 88 executable research tasks, has been released to test if frontier AI agents can achieve Recursive Self-Improvement (RSI). Domains include virtual cells, TPU kernels, chip design, and quant finance.
The protocol requires agents to iterate on visible data, with final artifacts evaluated on a hidden set. Opus 5 currently leads the 88-task leaderboard with a mean hidden-set score of 0.464. Task contributions are open for authorship credit.
More from Research
- Hannah Fry: How OpenAI has triggered an existential crisis in mathematics — AnnaCiaunica · 2026-10-15
- Watching AI evaluation shift from offline benchmarks to online eval — vboykis · 2026-10-15
- StartLux-Decision debuts RL-trained calibrated decision models, 27B scores 72.8 — startlux-models · 2026-10-15
- A third of all math preprints in 9 months were written with AI, researcher says — IgorCarron · 2026-10-15
- AAAI/ACM AIES paper interviews 15 data scientists on why responsible AI practice is hard to sustain — ChinasaTOkolo · 2026-10-15
- Schmidt Sciences awards $10M to 19 AI humanities research teams — OdedRechavi · 2026-10-15