כתבה
arXiv cs.LG ·
Agentic AutoRAG: פיתוח רשת רצפים על ידי סוכנים רציונליים
Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
Agentic AutoRAG מציע פיתוח רשת רצפים על ידי סוכנים רציונליים. הפיתוח כולל שימוש במודלי GPT-5 ו-Gemini.
תקציר מקורי באנגליתarXiv:2610.08452v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimization problem over many interacting choices, from chunking and embedding model to reranking and generation. Existing optimizers, from greedy search to Bayesian optimization, reduce each trial to an aggregate score and search without modeling why a configuration performed as it did, even though the retrieved chunks already provide evidence about whether each failure occurred during retrieval or after it. We introduce Agentic AutoRAG, an LLM-agent optimizer for multi-objective RAG hyperparameter optimization with retrieval-versus-generation failur
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית