Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
arXiv:2609.18366v1 Announce Type: new 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…
Read the full story at arXiv cs.AI ↗
ImpactMinor 15/100
Why it mattersRule-based estimate: event keywords (+4), soft/evergreen signals; trust 6/10.
RegionsGlobal
Published3 d ago (Thu, 17 Sep 2026 04:00:00 GMT)
RetrievedThu, 17 Sep 2026 15:30:40 GMT via rss
ClassifiedThu, 17 Sep 2026 15:30:51 GMT by heuristic
AuthorGuojun Zhu, Xunheng Huang, Peng Yin, Jiahui Xie, Sanguo Zhang, Doudou Zhou