Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration

v1v2v3 (latest)

Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration

27 May 2025

ArXiv (abs)PDF HTML

Papers citing "Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration"

6 / 6 papers shown

Title
ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models Biddut Sarker Bijoy Mohammad Saqib Hasan Pegah Alipoormolabashi Avirup Sil A. Balasubramanian Niranjan Balasubramanian LLMAG 8 0 0 02 Sep 2025
A Comprehensive Survey on Long Context Language Modeling Jiaheng Liu Dawei Zhu Zhiqi Bai Yancheng He Huanxuan Liao ... Bo Zheng Wangchunshu Zhou Wenhao Huang Sujian Li Zhenru Zhang LLMAG 184 28 0 20 Mar 2025
Why Do Multi-Agent LLM Systems Fail? Mert Cemri Melissa Z. Pan Shuyi Yang Lakshya A Agrawal Bhavya Chopra ... Dan Klein Kannan Ramchandran Matei A. Zaharia Joseph E. Gonzalez Ion Stoica LLMAG 354 80 0 17 Mar 2025
Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving Qihui Zhou Peiqi Yin Pengfei Zuo James Cheng CLL 160 3 0 01 Mar 2025
LongAttn: Selecting Long-context Training Data via Token-level Attention Longyun Wu Dawei Zhu Guangxiang Zhao Zhuocheng Yu Junfeng Ran Xiangyu Wong Lin Sun Sujian Li 191 3 0 24 Feb 2025
NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens Cunxiang Wang Ruoxi Ning Boqi Pan Tonghui Wu Qipeng Guo ... Guangsheng Bao Xiangkun Hu Zheng Zhang Qian Wang Yue Zhang RALM 307 14 0 18 Mar 2024