- Score 82
- Official
GRAFT: Execution-Guided Genetic Recombination for Agent Design
arXiv:2611.23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordination, and verification. This search, however, is typically guided by aggregate fitness alone, which hides the instance-l
So what
What this event means by reading role—not a longer recap.
- BuilderIf you auto-tune agent architectures, feeding per-parent success/failure traces into crossover may beat aggregate-fitness search without extra task executions.
- ResearcherAblations show execution evidence improves accuracy with initialization, search rules, repair policies, and budgets fixed, supporting instance-level feedback ov
Score dimensions
Higher total means read first. Each bar is one factor we use to rank the system pool. How we score