Papers & Research
Intuitor (Learning to Reason Without External Rewards)
Paper: models can learn to reason without external rewards
A mind-bending paper showing that reinforcement learning with internal or even random rewards can improve reasoning models. Intuitor matched or exceeded some GRPO results (the external-reward framework DeepSeek popularized with R1) when finetuning Qwen2.5 3B, questioning how much of RL's gains come from the reward signal itself.
3B Qwen2.5 model size where Intuitor matched or exceeded GRPO results