Comments50 pages, 4 figures. v3: expanded to a unified 69-paper corpus through July 31, 2026; adds restored-state identification results, blind coding of a 42-paper full-text subset, a source-located reporting audit, the CA-ID Card, and replay-fidelity analysis
ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems
ATLAS: 大规模软件生态系统的智能体分类体系
Junyi Lu, Mengyao Lyu, Jiahui Wu, Lei Yu, Chengwei Liu, Fengjun Zhang, Li Yang, Chun Zuo, Yang Liu
机构
*
Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
;
University of Chinese Academy of Sciences(中国科学院大学)
;
Nanyang Technological University(南洋理工大学)
;
Nankai University(南开大学)
;
Sinosoft Company Limited(中软国际有限公司)
SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents
SciVisAgentBench:用于评估科学数据分析和可视化代理的基准测试
Kuangshi Ai, Haichao Miao, Kaiyuan Tang, Nathaniel Gorski, Jianxin Sun, Guoxi Liu, Helgi I. Ingolfsson, David Lenz, Hanqi Guo, Hongfeng Yu, Teja Leburu, Michael Molash, Bei Wang, Tom Peterka, Chaoli Wang, Shusen Liu
机构
*
University of Notre Dame(圣母大学)
;
Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)
;
University of Utah(犹他大学)
;
University of Nebraska–Lincoln(内布拉斯加大学林肯分校)
;
The Ohio State University(俄亥俄州立大学)
;
Argonne National Laboratory(阿贡国家实验室)
;
Anthropic PBC
What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md Files
是什么阻碍了智能体技能的可复用性?来自13.8万个SKILL.md文件的证据
Chi Zhang, Yimin Liu, Xinze Chen, Ping Ji
机构
*
The Graduate Center, City University of New York(纽约城市大学研究生中心)
;
The Ohio State University(俄亥俄州立大学)
;
Hunter College, City University of New York(纽约城市大学亨特学院)
Comments171 pages. Formalized in Lean 4 with Mathlib: 240 theorems in the elaborated environment, 141 audited headline results, cold-compiling from a clean checkout with zero custom axioms. Source, theorem-by-theorem contract, and reproducible axiom audit: https://github.com/selfreferencing/TSE_Formal. Companion to Agentic Capital