paper / robertarail / May 13 / failedThe Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
paper / robertarail / May 13 / failedAI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
paper / robertarail / May 13 / failedSouper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
paper / robertarail / May 13 / failedAIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents