A Qwen3-4B RL harness reproduction tests transfer from TREC 32K to 256K

ben_burtenshaw · x · 2026-07-23

A minimal reproduction of the “language model harnesses are compositional generalizer” idea using a small, reproducible setup.

The follow-up note clarifies the assumptions: smaller model, frozen subcaller, shorter strategy training, lower subcall budgets, and no trajectory-similarity measurements yet.

Related event: Developer Creates Runnable RL Harness Prototype with Qwen3-4B(2 posts)→

Original post →

More from coding & agent

coding & agent channel →