Harness Engineering for Self-Improvement
Original excerpt
Edits are only applied to the harness workspace. the runs directory, tracer, verifier, and LLM configuration are read-only, which disables a set of reward hacking (e.g disabling the verifier, swapping the model, or raising the reasoning budget) and thus it can keep every recorded gain attributable to harness edits.
Context
Decision observability : every edit is paired with a prediction for the next round to validate. An agent (“Evolve agent”) reads the repo and decides which component to edit, and then produces the edit and the reasoning behind it. Every edit is a file-level, falsifiable claim and can be verified in the next round, under two constraints: (1) (2) Edits are evidence-driven, with a manifesto entry: the failure evidence’s name, the inferred root cause, the targeted fix, and a predicted impact comprising both expected fixes and at-risk regressions.