Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.08699 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909988934385664 |
|---|---|
| author | Tao, Zhengwei Li, Bo Wu, Jialong Yan, Guochen Zhang, Huanyao Xu, Jiahao Mi, Haitao Zhang, Wentao |
| author_facet | Tao, Zhengwei Li, Bo Wu, Jialong Yan, Guochen Zhang, Huanyao Xu, Jiahao Mi, Haitao Zhang, Wentao |
| contents | Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of robust agents is hindered by the scarcity of high-quality training data that reflects the noise and complexity of real-world retrieval environments. Conventional manual annotation is unscalable and often fails to capture the dynamic reasoning strategies required to handle retrieval failures. To bridge this gap, we introduce RAGShaper, a novel data synthesis framework designed to automate the construction of RAG tasks and robust agent trajectories. RAGShaper incorporates an InfoCurator to build dense information trees enriched with adversarial distractors spanning Perception and Cognition levels. Furthermore, we propose a constrained navigation strategy that forces a teacher agent to confront these distractors, thereby eliciting trajectories that explicitly demonstrate error correction and noise rejection. Comprehensive experiments confirm that models trained on our synthesized corpus significantly outperform existing baselines, exhibiting superior robustness in noise-intensive and complex retrieval tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08699 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis Tao, Zhengwei Li, Bo Wu, Jialong Yan, Guochen Zhang, Huanyao Xu, Jiahao Mi, Haitao Zhang, Wentao Computation and Language Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of robust agents is hindered by the scarcity of high-quality training data that reflects the noise and complexity of real-world retrieval environments. Conventional manual annotation is unscalable and often fails to capture the dynamic reasoning strategies required to handle retrieval failures. To bridge this gap, we introduce RAGShaper, a novel data synthesis framework designed to automate the construction of RAG tasks and robust agent trajectories. RAGShaper incorporates an InfoCurator to build dense information trees enriched with adversarial distractors spanning Perception and Cognition levels. Furthermore, we propose a constrained navigation strategy that forces a teacher agent to confront these distractors, thereby eliciting trajectories that explicitly demonstrate error correction and noise rejection. Comprehensive experiments confirm that models trained on our synthesized corpus significantly outperform existing baselines, exhibiting superior robustness in noise-intensive and complex retrieval tasks. |
| title | RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.08699 |