Skip to main content
Search

# Elite (Explore-then-Integrate)

1 related articles

Subscribe to updates
  1. arXiv

    Coding agents evolve without running candidates: Elite lifts SWE-bench Pro from 60.0% to 85.6% with zero candidate task evaluations

    Self-improving coding agents usually run candidate versions on downstream tasks and let scores decide which lineage continues, so wider exploration raises evaluation cost. Elite instead implements several focused changes independently from the same parent, inspects the mechanisms in those executable programs, and reimplements a compatible subset as one descendant, using only deterministic structural and operational checks inside the loop. On a 60-task SWE-bench Pro subset, Elite raises the initial agent from 60.0% to 85.6% with zero candidate task evaluations, cutting observed evolution wall-clock time by 8.8x and 3.2x relative to DGM and HGM.

You’re all caught up