R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
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.
Code (3)
Tasks
MemorizationRAGRetrievalRetrieval-augmented GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on c…
RAGReinforcement Learning (RL)DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
Multimodal large language models (MLLMs) have advanced visual understanding and reasoning, yet their static parametric knowledge limits their ability to address knowledge-intensive and dynamically evolving open-world pro…
Reinforcement LearningO$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to-date information. While enabling LLMs t…
Answer GenerationOpen-Ended Question AnsweringQuestion AnsweringWorld KnowledgeFrom Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for hand…
Information RetrievalRetrievalIncentivizing Reasoning for Advanced Instruction-Following of Large Language Models
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive so…
Instruction FollowingReinforcement Learning (RL)