Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains — mentioned by nbardy

Mon, 13 Jul 2026 10:28:55 GMT

These are true and it does make theses fields the first to fall, but also the hype comes form the fact that it can escape these conditions as well: - generalize to non verifiable domains (https://arxiv.org/abs/2507.17746)[This is on going work but has had steady progress in many angles of attack) - Visual Reasoning is alive and well in video diffusion and image models(see recent works around using diffusion model priors as world model features for physics reasoning) - Prior art exists for anything humans can do online?(Is this one even a hold back?)

Paper and discussion history. A mention is not an endorsement.

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains — mentioned by jmalicki

Sat, 20 Jun 2026 15:55:50 GMT

The most advanced training data is in the form of rubrics as rewards. A human asks a question, then writes rubrics to judge the LLMs response, so rather than evaluating a specific response, those rubrics can live on as the LLM evolves and gives different answers. There are more complex variants as well, but that's the basic principle. https://arxiv.org/abs/2507.17746

Paper and discussion history. A mention is not an endorsement.

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains · HackerPapers discussions

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains — mentioned by nbardy

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains — mentioned by jmalicki