OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models

arXiv:2604.19766v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex, multi-hop problems. While recent dynamic retrieval strategies offer improvements, they face two key challenges: 1) irrelevant retrieved noise can misdirect the reasoning process, and 2) processing full documents incurs prohibitive computational and latency costs. To address these issues, we propose OThink-SRR1, a framework that enhances large models with an iterative Search-Refine-Reason process trained via reinforcement learning. Its core Refine stage distills retrieved documents into concise, relevant facts before reasoning. We introduce GRPO-IR, an end-to-end reinforcement learning algorithm that rewards accurate evidence identification while penalizing excessive retrievals, thus training the model to be both focused and efficient. Experiments on four multi-hop QA benchmarks show our approach achieves superior accuracy over strong baselines while using fewer retrieval steps and tokens. This positions OThink-SRR1 as a potent foundational model for information-seeking agents.

Related

• KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
• CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
• MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
• Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
• Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation

Source: arXiv cs.AI | 2026-04-23