3 papers
cs.IR2026
Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation
Shuguang Jiao, Chengkai Huang, Shuhan Qi +6
Agentic Retrieval-Augmented Generation interleaves retrieval and reasoning for multi-hop QA and complex knowledge tasks. As reasoning trajectories lengthen, failures become more fr…
cs.CV2026
Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
Dingkun Zhang, Shuhan Qi, Yulin Wu +3
Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token numbers. Existing effor…
cs.IR2026
PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation
Shuguang Jiao, Xinyu Xiao, Yunfan Wei +4
Retrieval-augmented generation (RAG) has become a powerful framework for enhancing large language models in knowledge-intensive and reasoning tasks. However, as reasoning chains de…