# Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation

arXiv: https://arxiv.org/abs/2505.17391 · HTML: https://mlsanity.com/paper/2505.17391/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [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)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [ComposerX: Multi-Agent Symbolic Music Composition with LLMs](https://mlsanity.com/paper/2404.18081/) (2024)
- [ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding](https://mlsanity.com/paper/2501.07861/) (2025)
- [RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning](https://mlsanity.com/paper/2503.12759/) (2025)
- [RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects](https://mlsanity.com/paper/2501.18365/) (2025)
- [SiReRAG: Indexing Similar and Related Information for Multihop Reasoning](https://mlsanity.com/paper/2412.06206/) (2024)
- [Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering](https://mlsanity.com/paper/2502.14245/) (2025)
- [Enhance Image-to-Image Generation with LLaVA-generated Prompts](https://mlsanity.com/paper/2406.01956/) (2024)
- [Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling](https://mlsanity.com/paper/2504.15296/) (2025)
- [RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization](https://mlsanity.com/paper/2502.10993/) (2025)
- [Data Augmentation Through Random Style Replacement](https://mlsanity.com/paper/2504.10563/) (2025)
- [Scam Detection for Ethereum Smart Contracts: Leveraging Graph Representation Learning for Secure Blockchain](https://mlsanity.com/paper/2412.12370/) (2024)
- [Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering](https://mlsanity.com/paper/2503.22303/) (2025)

## Built on by (most cited first, 5 of 5)

- [Reinforcement Learning Foundations for Deep Research Systems: A Survey](https://mlsanity.com/paper/2509.06733/) (2025)
- [How Many Tools Should an LLM Agent See? A Chance-Corrected Answer](https://mlsanity.com/paper/2605.24660/) (2026)
- [Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum](https://mlsanity.com/paper/2603.05256/) (2026)
- [Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents](https://mlsanity.com/paper/2601.21699/) (2026)
- [An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2506.07411/) (2025)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) grounds large language models (LLMs) in up-to-date external evidence, yet existing multi-hop RAG pipelines still issue redundant subqueries, explore too shallowly, or wander through overly long search chains. We introduce EVO-RAG, a curriculum-guided reinforcement learning framework that evolves a query-rewriting agent from broad early-stage exploration to concise late-stage refinement. EVO-RAG couples a seven-factor, step-level reward vector (covering relevance, redundancy, efficiency, and answer correctness) with a time-varying scheduler that reweights these signals as the episode unfolds. The agent is trained with Direct Preference Optimization over a multi-head reward model, enabling it to learn when to search, backtrack, answer, or refuse. Across four multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue, and Bamboogle), EVO-RAG boosts Exact Match by up to 4.6 points over strong RAG baselines while trimming average retrieval depth by 15 %. Ablation studies confirm the complementary roles of curriculum staging and dynamic reward scheduling. EVO-RAG thus offers a general recipe for building reliable, cost-effective multi-hop RAG systems.