Automated Discovery Has No Universally Superior Harness
Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses. However, in practice these are composite systems combining several design choices about archives, parent selection, exploration, and budget allocation into a single recipe. Because discovery runs are expensive and inherently stochastic, existing harnesses are often compared using too few independent trials to distinguish key methodological improvements from run-to-run variance. We systematically decompose OpenEvolve-style evolutionary search and the TTT-Discover search harness into its
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “Automated Discovery Has No Universally Superior Harness” ≈ “strands-agents/harness-sdk””
- FuzzyOverlapping authors or contributors · 62%microsoft/ML-For-Beginners →
“Shared author/contributor keys: gupta”
- FuzzySimilar title/name (fuzzy) · 59%browser-use/browser-harness →
“Fuzzy title match (0.73): “Automated Discovery Has No Universally Superior Harness” ≈ “browser-use/browser-harness””
- LinkedLinked via arxiv author · 85%Akshat Gupta →
“Automated Discovery Has No Universally Superior Harness”
- LinkedLinked via arxiv author · 85%Jermaine Lei →
“Automated Discovery Has No Universally Superior Harness”
- LinkedLinked via arxiv author · 85%Alexander Lu →
“Automated Discovery Has No Universally Superior Harness”
- LinkedLinked via arxiv author · 85%Gopala Anumanchipalli →
“Automated Discovery Has No Universally Superior Harness”
- LinkedLinked via arxiv author · 85%Leshem Choshen →
“Automated Discovery Has No Universally Superior Harness”