paper-with-me

홈 › Papers

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

2025-03-07 · Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, Ji-Rong Wen

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 challenging tasks such as mathematics and coding, they often rely on their internal knowledge to solve problems, which can be inadequate for time-sensitive or knowledge-intensive questions, leading to inaccuracies and hallucinations. To address this, we propose \textbf{R1-Searcher}, a novel two-stage outcome-based RL approach designed to enhance the search capabilities of LLMs. This method allows LLMs to autonomously invoke external search systems to access additional knowledge during the reasoning process. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. % effectively generalizing to out-of-domain datasets and supporting both Base and Instruct models. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.

📄 PDF Abstract BibTeX arXiv:2503.05592

Code (5)

RUCAIBox/R1-Searcher pytorch
rucaibox/r1-searcher-plus
rucaibox/simpledeepsearcher
terrierteam/pyterrier_rag
wlzhang2020/reasonrag pytorch

Tasks

RAGReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

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

2025-05-22 · Huatong Song, Jinhao Jiang, Wenqing Tian, Zhipeng Chen 외

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, generaliz…

MemorizationRAGRetrievalRetrieval-augmented Generation

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

2026-06-18 · Yanxi Chen, Weijie Shi, Yuexiang Xie, Boyi Hu 외 arxiv

This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment,…

Reinforcement LearningDomain Generalization

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

2025-01-22 · DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang 외

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary st…

Mathematical ReasoningMulti-task Language UnderstandingQuestion AnsweringReinforcement Learning (RL)

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

2026-02-17 · Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul 외 arxiv

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning cap…

Code Generation

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

2025-05-24 · Haoyuan Sun, Jiaqi Wu, Bo Xia, Yifu Luo 외

Standing in 2025, at a critical juncture in the pursuit of Artificial General Intelligence (AGI), reinforcement fine-tuning (RFT) has demonstrated significant potential in enhancing the reasoning capability of large lang…

Position