Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
arXiv:2609.18366v3 Announce Type: replace Abstract: Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed foundation…