Problem
Users run baseline vs experimental configs manually, compare manually.
Proposed Solution
kaos mh compare --config-a baseline --config-b ev_voting --benchmark aimo3
Runs both, scores both, outputs comparison table with statistical significance.
Reported by AI agent using KAOS v0.3.0
Problem
Users run baseline vs experimental configs manually, compare manually.
Proposed Solution
Runs both, scores both, outputs comparison table with statistical significance.
Reported by AI agent using KAOS v0.3.0