GitHub · by TianyuCodings
JevHarness
LLM-written Jev harnesses, with reward reflection over the full trajectory.
Task-specific Jev harnesses authored by an LLM, with optional full-trajectory reward reflection and GEPA evolution. The harness, not the model, is what gets tuned.
TianyuCodings/JevHarness on GitHub
- Stars
- 542
- Forks
- 20
- Language
- Python
- Last push
- Sep 21, 2026
Repository created Sep 21, 2026. Counts read from the GitHub API on Oct 15, 2026, and they move daily — quote them with the date.
