# GRASP: GRanularity-Aware Search Policy for Agentic RAG

arXiv: https://arxiv.org/abs/2607.10463 · HTML: https://mlsanity.com/paper/2607.10463/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 18 of 18)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [LMDX: Language Model-based Document Information Extraction and Localization](https://mlsanity.com/paper/2309.10952/) (2023)
- [Instruct and Extract: Instruction Tuning for On-Demand Information Extraction](https://mlsanity.com/paper/2310.16040/) (2023)
- [A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces](https://mlsanity.com/paper/2602.03442/) (2026)
- [DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision](https://mlsanity.com/paper/2510.05691/) (2025)
- [MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval](https://mlsanity.com/paper/2510.27569/) (2025)
- [Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation](https://mlsanity.com/paper/2509.20162/) (2025)

## Built on by (most cited first, 1 of 1)

- [SEEDS: Preview-Guided Evidence Admission for Search Agents](https://mlsanity.com/paper/2610.12932/) (2026)

## Abstract (arXiv)

Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers. However, it remains challenging for models to decide when to retrieve, whether to use lexical matching or semantic similarity, and how to control context granularity to prevent irrelevant tokens from interfering with agent reasoning. In this paper, we introduce GRASP, a reinforcement learning (RL) framework for training agents to adaptively coordinate complementary retrieval tools during multi-step reasoning. GRASP provides the agent with semantic search, keyword search, and paragraph-reading actions, enabling it to retrieve sentence-level evidence and expand further context only when needed. We train the policy with a reward that jointly accounts for answer accuracy, grounded reading, complementary search, and turn efficiency. Experiments on multi-hop reasoning benchmarks show that GRASP improves both retrieval recall and downstream question answering performance compared with single-step retrieval, prompting-based agentic RAG, and RL-based retrieval baselines. Qualitative and ablation analyses show that the learned policy develops interpretable skimming and scanning behavior: it uses semantic search for broad exploration, paragraph reading for local verification, and keyword search for entity-specific evidence. These results suggest that learning to coordinate retrieval signals and context granularity is critical for agent's correct reasoning.