CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG
CARROT:一种用于RAG的学得式成本约束检索优化系统
专题命中 规划推理 :reasoning(abstract);分类 cs.CL
AI总结 CARROT通过MCTS和配置代理优化RAG检索,提升检索效率与准确性,实验显示性能提升达30%。
Comments Accepted to ICDE 2026. Updated title (previously "CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation")