cs.CLNov 6, 2026

MARS: Training Multilingual Search Agents for Retriever-Free Evidence Acquisition

Authors: Rui Qi, Yunlong Liang, Yufeng Chen, Jinan Xu, Fandong Meng, Kaiyu Huang

Organizations: Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education · School of Computer Science and Technology, Beijing Jiaotong University · Pattern Recognition Center, WeChat AI, Tencent Inc., China

Abstract

Existing multilingual retrieval-augmented generation relies heavily on learned retrievers and similarity-based ranking from multilingual collections, which are vulnerable to cross-lingual retrieval errors and indexing overhead. In this paper, we explore retriever-free multilingual search, where the model directly interacts with raw corpora through executable shell commands. This paradigm shifts the bottleneck to multilingual search action generation, where exact search is sensitive to entity surface forms and outcome-only supervision provides limited guidance for multi-turn search. To address these challenges, we propose MARS, a multilingual search agent in direct corpus interaction (DCI) with reinforcement learning (RL). MARS introduces corpus-native entity grounding to recover reliable lexical anchors from corpus evidence, mitigating failure to retrieve evidence. Meanwhile, we present a redundancy-aware search reward to encourage concise and effective search trajectories, addressing training collapse in RL of multilingual scenarios. Experiments show that \ours~consistently outperforms strong retrieval-based and DCI baselines, while demonstrating robust cross-lingual generalization and substantially reducing redundant corpus interactions.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

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

    Apr 28, 2026Rui Qi, Fengran Mo, Sijin Lu +3Multilingual RAGRetrieval-Augmented Generation

  2. CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG

    Apr 28, 2026Nayeon Lee, Jiwoo Song, Byeongcheol KangAgentic RAGRetrieval-Augmented Generation

  3. All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG

    Apr 22, 2026Dan Wang, Guozhao Mo, Yafei Shi +9Multilingual RAGRetrieval-Augmented Generation