3 papers
cs.CL2026
GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning
Jun Chen, Yongchao Liu, Pengyu Qiu +6
Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop questions, multi-turn retrieval-au…
cs.DC2026
Bole: Efficient Tree Speculation for Hybrid-Attention Language Models
Li Wang, Yi Su, Xiabao Wu +9
Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memo…
cs.PF2026
Decoupled Attention Fusion: Accelerating RAG with Efficient KV Cache Reuse
Xiabao Wu, Wentao Liu, Yongchao Liu +1
Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations in Large Language Models (LLMs) but suffers from prohibitive Time-To-First-Token (TTFT) latency in long-co…