# R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.17005 · HTML: https://mlsanity.com/paper/2505.17005/

## Key facts

- Cited by 30 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 23 of its 33 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- [SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs](https://mlsanity.com/paper/2404.13081/) (2024)
- [Atom of Thoughts for Markov LLM Test-Time Scaling](https://mlsanity.com/paper/2502.12018/) (2025)
- [Long Term Memory: The Foundation of AI Self-Evolution](https://mlsanity.com/paper/2410.15665/) (2024)
- [OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain](https://mlsanity.com/paper/2412.13018/) (2024)
- [Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks](https://mlsanity.com/paper/2410.01428/) (2024)
- [AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation](https://mlsanity.com/paper/2501.10053/) (2025)

## Built on by (most cited first, 30 of 30)

- [UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.02544/) (2025)
- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [WideSearch: Benchmarking Agentic Broad Info-Seeking](https://mlsanity.com/paper/2508.07999/) (2025)
- [Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents](https://mlsanity.com/paper/2510.14967/) (2025)
- [SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models](https://mlsanity.com/paper/2509.23863/) (2025)
- [Towards Effective Code-Integrated Reasoning](https://mlsanity.com/paper/2505.24480/) (2025)
- [ClawGym: A Scalable Framework for Building Effective Claw Agents](https://mlsanity.com/paper/2604.26904/) (2026)
- [Reinforcement Learning Foundations for Deep Research Systems: A Survey](https://mlsanity.com/paper/2509.06733/) (2025)
- [GTM: Simulating the World of Tools for AI Agents](https://mlsanity.com/paper/2512.04535/) (2025)
- [Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement](https://mlsanity.com/paper/2506.05154/) (2025)
- [VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking](https://mlsanity.com/paper/2508.04026/) (2025)
- [ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards](https://mlsanity.com/paper/2510.00568/) (2025)
- [HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation](https://mlsanity.com/paper/2510.07794/) (2025)
- [EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes](https://mlsanity.com/paper/2509.00877/) (2025)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)
- [DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents](https://mlsanity.com/paper/2602.07035/) (2026)
- [GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning](https://mlsanity.com/paper/2601.08621/) (2026)
- [JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG](https://mlsanity.com/paper/2601.21916/) (2026)
- [RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection](https://mlsanity.com/paper/2509.26048/) (2025)
- [PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning](https://mlsanity.com/paper/2508.21104/) (2025)
- [ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation](https://mlsanity.com/paper/2608.04436/) (2026)
- [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026)
- [From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development](https://mlsanity.com/paper/2509.23071/) (2025)
- [Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models](https://mlsanity.com/paper/2510.18303/) (2025)
- [IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning](https://mlsanity.com/paper/2602.03468/) (2026)
- [Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents](https://mlsanity.com/paper/2609.22486/) (2026)
- [Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2510.09156/) (2025)
- [SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks](https://mlsanity.com/paper/2605.09038/) (2026)
- [Test-Time Deep Thinking to Explore Implicit Rules](https://mlsanity.com/paper/2605.24828/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-Augmented Generation (RAG) helps by injecting external information, but current methods often are costly, generalize poorly, or ignore the internal knowledge of the model. In this paper, we introduce R1-Searcher++, a novel framework designed to train LLMs to adaptively leverage both internal and external knowledge sources. R1-Searcher++ employs a two-stage training strategy: an initial SFT Cold-start phase for preliminary format learning, followed by RL for Dynamic Knowledge Acquisition. The RL stage uses outcome-supervision to encourage exploration, incorporates a reward mechanism for internal knowledge utilization, and integrates a memorization mechanism to continuously assimilate retrieved information, thereby enriching the model's internal knowledge. By leveraging internal knowledge and external search engine, the model continuously improves its capabilities, enabling efficient retrieval-augmented reasoning. Our experiments demonstrate that R1-Searcher++ outperforms previous RAG and reasoning methods and achieves efficient retrieval. The code is available at https://github.com/RUCAIBox/R1-Searcher-plus.