Research2026-05-12
AgentGA: Evolving Code Solutions in Agent-Seed Space
Source: Arxiv CS.AI
arXiv:2604.14655v2 Announce Type: replace Abstract: We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the task prompt plus optional parent archives that initialize a fresh workspace. The outer loop searches over these reusable starting...
arxivpapersagents