Lecture 10 of CS224R Spring 2026 is a guest lecture by Noam Brown of OpenAI, and it makes one argument: reasoning models open a new scaling dimension by moving compute from training to inference. He starts with his own poker AI work, then uses backgammon, chess, and Go to show that thinking longer at inference time has always paid off. Next comes how LLMs got there: chain of thought, majority voting, o1/o3, GRPO, and DeepSeek-R1-Zero. The second half argues the field needs to rethink itself for large-scale test-time compute: multi-agent systems, evaluation as score versus compute, and the budget assumptions behind safety evaluations. The deck is mostly figures, so this post covers only the points visible on the slides.
CME295 Lecture 6 breaks reasoning models into three pieces: emit a reasoning chain before the answer, run RL on verifiable rewards like "is the answer correct," and use GRPO, which takes the group's average reward as the baseline instead of training a value model. RL alone took DeepSeek-R1-Zero from 15.6% to 71.0% pass@1 on AIME 2024, and distilling R1's traces into Qwen-32B beat running RL on the 32B model directly.
The 2026 CME295 Lecture 4 (October 16) gives RL its own lecture, with seven syllabus items: mathematical conventions, reward design, policy gradients, limitations, PPO, GRPO, and on-policy distillation. This post walks the math ahead of class: start from ∇log π times a score. SFT uses a score of 1, PPO estimates it with a value model, GRPO uses the group mean, and on-policy distillation uses the teacher's per-token log-prob gap. In the Qwen3 report, starting from the same checkpoint, RL reached 67.6 on AIME'24 with 17,920 GPU hours, while on-policy distillation reached 74.4 with about 1/10 of that (1,800 hours).
Using a guess-a-number-from-1-to-16 game, Daniel Fried frames RL as an extension of SFT: he names SFT's three gaps (task mismatch, no learning from failures, never seeing its own mistakes), then derives ReST, REINFORCE, baselines, and GRPO/DrGRPO in turn. All four compute log-probabilities of the tokens the agent itself generated; they differ only in the weight each token gets.
Using a bug-fix coding task, Graham Neubig takes Lecture 9's policy gradient into practice: a critic, GAE, or a PRM to credit individual turns; importance ratios and clipping to handle stale data in async RL; and PPO, GRPO, CISPO, GSPO, and DAPO side by side in one table. The largest share goes to the reward itself — verifier errors, reward hacking, and exploration collapse — before closing with on-policy distillation.
MiniMind is an open-source project for training LLMs from scratch: a 64M Dense model and a 198M-A64M MoE model that run the entire chain — Pretrain → SFT → LoRA → DPO → PPO/GRPO/CISPO → Agentic RL — in ~2 hours on a single RTX 3090 at roughly 3 RMB (~$0.40). Every core algorithm is implemented natively in PyTorch with no high-level wrappers.
Three non-big-lab teams used different RL post-training strategies to produce benchmark dark horses in 2026: Ornith's self-improvement loop (GRPO), Nous Research's DataForge + Atropos execution-reward RL, and MiniMax's massive-scale RL across 200K real environments. Different strengths, but one shared proof point: post-training RL matters more than pretraining scale.
Lecture 16 moves from PPO to GRPO and RLVR. Math, code, and environment outcomes provide scalable rewards and avoid some preference-model overoptimization, but group-normalized advantages introduce difficulty and length bias while rollout infrastructure becomes the dominant cost.