GRASP: RL Framework for Adaptive Retrieval in Agentic RAG

Jul 14, 2026

Researchers introduce GRASP, a reinforcement learning framework that enables agents to adaptively coordinate semantic search, keyword search, and paragraph reading during multi-step reasoning. The policy learns to control context granularity, leading to improved retrieval recall and question answering performance on multi-hop benchmarks. The learned strategies include interpretable skimming and scanning behaviors.

Why it matters: This work advances agentic retrieval-augmented generation by enabling dynamic and context-aware retrieval strategies, which are important for accurate multi-step reasoning.

Full story at: arXiv Information Retrieval ↗