Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs
Post training a language model to reason means updating its weights. Supervised finetuning and reinforcement learning both place the acquired capability inside the model where it cannot be inspected cannot be checked step by step and cannot be moved to another model. We argue that for tasks whose intermediate steps admit verification, reasoning is better placed outside the base models weights as…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
