mlsanityData to 14 Oct 2026

CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation

arXiv 2604.25182 ↗First posted 28 Apr 2026cs.CL cs.IRcited by 1

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

A multilingual collection may contain useful knowledge in other languages to supplement and correct the facts in the original language for Retrieval-Augmented Generation (RAG). However, the vanilla approach that simply concatenates multiple pieces of knowledge from different languages into the context may fail to improve effectiveness due to the potential disparities across languages. To better leverage multilingual knowledge, we propose CroSearch-R1, a search-augmented reinforcement learning framework to integrate multilingual knowledge into the Group Relative Policy Optimization (GRPO) process. In particular, the approach adopts a multi-turn retrieval strategy with cross-lingual knowledge integration to dynamically align the knowledge from other languages as supplementary evidence into a unified representation space. Furthermore, we introduce a multilingual rollout mechanism to optimize reasoning transferability across languages. Experimental results demonstrate that our framework effectively leverages cross-lingual complementarity and improves the effectiveness of RAG with multilingual collections.

Key facts. Cited by 1 paper 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 35 of its 49 references that are in the map. First posted on arXiv 28 Apr 2026.

Builds on

35 of 49 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoning4 Jun

Other references · 34

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  5. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  9. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  10. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  11. 2020MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answeringcited by 153
  12. 2024IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologuescited by 40
22 more
  1. 2025Parametric Retrieval Augmented Generationcited by 38
  2. 2025Entropy-based Exploration Conduction for Multi-step Reasoningcited by 29
  3. 2024Retrieval-augmented generation in multilingual settingscited by 27
  4. 2024Prototypical Reward Network for Data-Efficient RLHFcited by 22
  5. 2024A Survey of Conversational Searchcited by 22
  6. 2025Investigating Language Preference of Multilingual RAG Systemscited by 22
  7. 2025Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Taskcited by 12
  8. 2025UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversationscited by 12
  9. 2026OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAGcited by 11
  10. 2025XRAG: Cross-lingual Retrieval-Augmented Generationcited by 9
  11. 2023Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMscited by 8
  12. 2025CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMscited by 8
  13. 2025Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigationcited by 8
  14. 2024Enhancing Multilingual Information Retrieval in Mixed Human Resources Environments: A RAG Model Implementation for Multicultural Enterprisecited by 7
  15. 2025Parametric Retrieval-Augmented Generation using Latent Routing of LoRA Adapterscited by 6
  16. 2024MIND Your Language: A Multilingual Dataset for Cross-lingual News Recommendationcited by 5
  17. 2025Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentationscited by 5
  18. 2026StaRPO: Stability-Augmented Reinforcement Policy Optimizationcited by 5
  19. 2025Boosting Data Utilization for Multilingual Dense Retrievalcited by 3
  20. 2025SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Modelscited by 2
  21. 2026Cost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural Advisorycited by 2
  22. 2026SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Planscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation
  2. 2025MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
  3. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
  4. 2025Multi-hop Reasoning via Early Knowledge Alignment
  5. 2025R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
  6. 2025RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
  7. 2025Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
  8. 2026OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models