4 papers · 1 filter
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
Zhiwei Li, Lei Zhu, Hao Gu +6
Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for e…
Stabilizing Efficient Reasoning with Step-Level Advantage Selection
Han Wang, Xiaodong Yu, Jialian Wu +4
Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While…
RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis
Zhengwei Tao, Bo Li, Jialong Wu +5
Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of r…
DocDancer: Towards Agentic Document-Grounded Information Seeking
Qintong Zhang, Xinjie Lv, Jialong Wu +8
Document Question Answering (DocQA) focuses on answering questions grounded in given documents, yet existing DocQA agents lack effective tool utilization and largely rely on closed…