Surrogate harness training: RL-training long-horizon agents entirely on synthetic environments

a1zhang · x · 2026-11-20

Alex Zhang presents surrogate harness training from the RLM paper, tackling the problem that very long tasks (multi-day rollouts, sparse rewards) are nearly impossible to RL-train directly.

This offers a viable path to RL-train expensive long-horizon agent tasks with synthetic data.

Related event: MIT Paper: LM Harnesses Are Compositional Generalizers, Not Crutches(10 posts)→

Original post →

More from coding & agent

coding & agent channel →