Mode collapse warning: RL rewards have increased but the ceiling hasn't moved; this point needs to be emphasized.

Stanford NLP demonstrated at ICML 2026 that by automating executors, pre-training and post-training of LLMs can be transformed into execution environments, using execution feedback to improve research efficiency. Two methods: evolutionary search outperforms GRPO (69.4% vs. 48.0%) in post-training tasks, and recipes found in pre-training tasks are faster than nanoGPT (19.7 minutes vs. 35.9 minutes), both completed within ten search rounds; reinforcement learning based on execution rewards is prone to mode collapse, which, while increasing average rewards, does not improve the upper bound. This work points the way for execution-oriented automated AI research.