Performance Foundations of Parallel & Distributed Reasoning Language Models
并行与分布式推理语言模型的性能基础
Maciej Besta, Leonard Schmidt, Lara Nonino, Robert Gerstenberger, Pierre Pang, Patrik Okanovic, Ales Kubicek, Tiancheng Chen, Baraq Lipshitz, Torsten Hoefler
机构
*
Department of Computer Science, Purdue University(普渡大学计算机科学系)
;
Department of Computer Science, Rice University(莱斯大学计算机科学系)
;
Ken Kennedy Institute, Rice University(莱斯大学肯尼迪研究所)
机构
*
Meituan Inc.(美团公司)
;
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院)
;
Beijing Institute of Technology(北京理工大学)
;
University of Edinburgh(爱丁堡大学)
机构
*
Hunan University(湖南大学)
;
Nanjing University(南京大学)
;
The Chinese University of Hong Kong(香港中文大学)
;
Zhejiang University(浙江大学)
;
Yale University(耶鲁大学)
;
Wuhan University of Science and Technology(武汉科技大学)
;
Southeast University(东南大学)
;
Stanford University(斯坦福大学)
机构
*
Meituan(美团)
;
MoE Key Lab of Artificial Intelligence(MoE人工智能重点实验室)
;
AI Institute(人工智能研究院)
;
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院)
;
MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
ProvenanceGuard: 基于MCP的LLM智能体的源感知事实性验证
Ander Alvarez, Santhiya Rajan, Alessandro Genuardi, Oliver Wirjadi, Samuel Mugel, Román Orús
机构
*
Multiverse Computing
;
Parque Cientifico y Tecnológico de Gipuzkoa(吉普斯夸科技园)
;
Centre for Social Innovation(社会创新中心)
;
Donostia International Physics Center(多诺斯蒂亚国际物理中心)
;
Ikerbasque Foundation for Science(伊克尔巴斯克科学基金会)
机构
*
Zhongguancun Academy(中关村学院)
;
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
;
University of Manchester(曼彻斯特大学)
;
Tongji University(同济大学)
CommentsAccepted to Findings of EMNLP 2026. 19 pages, 7 figures: 9-page main paper followed by limitations, ethics, acknowledgments, references, and appendices A-E. Project page: this https URL (https://sharryxr.github.io/ASIL/)
Comments19 pages, 4 figures, and 3 tables. Accepted at the Joint Workshop on Planning for Complex Real-World Applications (CAIPI) and Bridging the Gap Between AI Planning and (Reinforcement) Learning (PRL), co-located with IJCAI-ECAI 2026