Skip to main content
Search

Wentao Zhang

1 related articles

Subscribe to updates
  1. arXiv

    AgentEvolver lets agents self-evolve during task execution with a fixed foundation model, reporting 82.08% resolution on SWE-bench Pro Public

    The authors present AgentEvolver, a system that develops capabilities during task execution while keeping the foundation model fixed: eight entity families are exposed to revision through a common versioned lifecycle, a shared Runtime coordinates ongoing work, and persistent planning with recoverable context preserves task direction and supporting evidence; on SWE-bench Pro Public the team reports an 82.08% resolution rate, exceeding its reported baseline without evolution, and six application cases show retained capabilities entering later website, game, and research work while also documenting incomplete objectives and an unsuccessful strategy.

You’re all caught up