# RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning

arXiv: https://arxiv.org/abs/2503.12759 · HTML: https://mlsanity.com/paper/2503.12759/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [Building Math Agents with Multi-Turn Iterative Preference Learning](https://mlsanity.com/paper/2409.02392/) (2024)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction](https://mlsanity.com/paper/1905.08511/) (2019)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges](https://mlsanity.com/paper/2502.01612/) (2025)
- [REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering](https://mlsanity.com/paper/2402.17497/) (2024)

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

- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization](https://mlsanity.com/paper/2505.15107/) (2025)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs](https://mlsanity.com/paper/2507.09477/) (2025)
- [Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2505.11277/) (2025)
- [100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models](https://mlsanity.com/paper/2505.00551/) (2025)
- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey](https://mlsanity.com/paper/2504.10499/) (2025)
- [Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training](https://mlsanity.com/paper/2602.22576/) (2026)
- [MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains](https://mlsanity.com/paper/2603.00873/) (2026)
- [EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes](https://mlsanity.com/paper/2509.00877/) (2025)
- [Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?](https://mlsanity.com/paper/2510.16582/) (2025)
- [Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation](https://mlsanity.com/paper/2505.17391/) (2025)
- [GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning](https://mlsanity.com/paper/2604.20659/) (2026)
- [Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training](https://mlsanity.com/paper/2511.07328/) (2025)
- [Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning](https://mlsanity.com/paper/2603.22758/) (2026)
- [Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.20825/) (2025)
- [Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring](https://mlsanity.com/paper/2507.17442/) (2025)
- [UR2: Unify RAG and Reasoning through Reinforcement Learning](https://mlsanity.com/paper/2508.06165/) (2025)
- [LLP: LLM-Based Product Pricing in E-commerce](https://mlsanity.com/paper/2510.09347/) (2025)
- [DACL-RAG: Data Augmentation Strategy with Curriculum Learning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.10493/) (2025)
- [Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.15586/) (2025)
- [E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency](https://mlsanity.com/paper/2508.09023/) (2025)
- [LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning](https://mlsanity.com/paper/2510.07685/) (2025)
- [CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts](https://mlsanity.com/paper/2510.09278/) (2025)
- [Test-Time Strategies for More Efficient and Accurate Agentic RAG](https://mlsanity.com/paper/2603.12396/) (2026)
- [Quantifying Prior Dominance in RAG Systems](https://mlsanity.com/paper/2606.23695/) (2026)
- [Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG](https://mlsanity.com/paper/2607.02966/) (2026)
- [SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2610.11371/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting downstream performance. We introduce RAG-RL, an answer generation model trained not only to produce answers but also to identify and cite relevant information from larger sets of retrieved contexts, shifting some of the burden of identifying relevant documents from the retriever to the answer generator. Our approach uses curriculum learning, where the model is first trained on easier examples that include only relevant contexts. Our experiments show that these training samples enable models to acquire citation and reasoning skills with greater sample efficiency and generalizability, demonstrating strong model performance even as the number of irrelevant passages increases. We benchmark our methods on three open-domain multi-hop question answering datasets and report significant gains in answer and citation accuracy. Our experiments provide empirical insights into how easier training samples can give models stronger signals for learning specific skills (e.g., citation generation) and how different components of post-training (e.g., training set construction, rule-based rewards, training sample ordering, etc.) impact final model performance.