RoboPhD's validation-free Elo evolution outperforms GEPA and Autoresearch on three of four agent benchmarks under a tight 1500-evaluation budget.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets
RoboPhD's validation-free Elo evolution outperforms GEPA and Autoresearch on three of four agent benchmarks under a tight 1500-evaluation budget.