Pre-print: iterated creation, grading, and revision of data science projects by language models
cjmaddison · x · 2026-11-05
Rohan Alexander's team announced an arXiv pre-print, "Iterated creation, grading, and revision of data science projects by language models," exploring a closed loop where LLMs create, grade, and iteratively revise data science projects. The post is a bare announcement; method details are in the paper.
More from Research
- Stanford benchmark: frontier models reach best team deal in only 14% of conflicts — rohanpaul_ai · 2026-11-05
- RL theory monograph by Chen, Chi, Fan et al: Statistical Foundations of RL, a non-asymptotic view — burny_tech · 2026-11-05
- Weight-space programming reproduced: GPT-6.1 beats PPO baseline 21x, no open-weight model passes it — burny_tech · 2026-11-05
- Chinese AI Scientist completes 11,382-step experiment in 203 hours autonomously — yogthos · 2026-11-05
- 8% of Nature peer reviews since June 2025 are fully AI-generated, analysis finds — TuhinChakr · 2026-11-05
- HandsOn benchmark: best dexterous manipulation policy manages only 29.1% success on Core-50 — jiqizhixin · 2026-11-05