Cao Zihang - Blog

「抵近知识无人区」

【阅】本周阅读摘选2026-04-13 → 2026-04-19

本周阅读摘选 2026-04-13 → 2026-04-19 目录学术相关 Towards real-world human behavior simulation: benchmarking large language models on long-horizon, cross-scenario, heterogeneous behavior traces An introduction to double/debiased machine learning...

Posted by Cao Zihang on April 20, 2026

【阅】本周阅读摘选2026-04-06 → 2026-04-12

本周阅读摘选 2026-04-06 → 2026-04-12 目录学术相关技术技巧腾讯技术工程丨技术教科书：顶级开发团队设计的Harness工程项目源码什么样快速启动工具系统查询系统 Multi-Agent编排与任务系统 TUI Harness Engineering cloc丨Cou...

Posted by Cao Zihang on April 13, 2026

【阅】本周阅读摘选2026-03-30 → 2026-04-05

本周阅读摘选 2026-03-30 → 2026-04-05 目录学术相关 Beyond Means: A Dynamic Framework for Predicting Customer Satisfaction Search games with predictions 娱乐 Leveraging LLM-based agents for social science research: insights from...

Posted by Cao Zihang on April 7, 2026

【阅】本周阅读摘选2026-03-23 → 2026-03-29

本周阅读摘选 2026-03-23 → 2026-03-29 目录学术相关 Diversity of interactions within connectivist learning context: insights from flow of collective attention 计量经济圈丨全网最全的社科计量方法手册(含实操), 社会科学计量模型一网打尽(收藏级) 学术相关 Diversity of interactions wit...

Posted by Cao Zihang on March 30, 2026

【阅】本周阅读摘选2026-03-16 → 2026-03-22

本周阅读摘选 2026-03-16 → 2026-03-22 目录学术相关 Algorithmic targeting and the precision-recall tradeoff 娱乐 MASS 学术相关 Algorithmic targeting and the precision-recall tradeoff 1 娱乐 MASS AI-powered social simulation plat...

Posted by Cao Zihang on March 23, 2026

【阅】本周阅读摘选2026-03-09 → 2026-03-15

本周阅读摘选 2026-03-09 → 2026-03-15 目录学术相关 The decision-making process and impact of individual decisions for joint consumption Large language models for market research: a data-augmentation approach 学术相关 The decision-making p...

Posted by Cao Zihang on March 16, 2026

【阅】本周阅读摘选2026-03-02 → 2026-03-08

本周阅读摘选 2026-03-02 → 2026-03-08 目录技术技巧 DeepCode: open agentic coding 娱乐 dexter 技术技巧 DeepCode: open agentic coding 1 github 娱乐 dexter An autonomous agent for deep financial research Li, ...

Posted by Cao Zihang on March 9, 2026

【阅】本周阅读摘选2026-02-23 → 2026-03-01

本周阅读摘选 2026-02-23 → 2026-03-01 目录学术相关 AgentLTV: an agent-based unified search-and-evolution framework for automated lifetime value prediction MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem 娱乐 ...

Posted by Cao Zihang on March 2, 2026

【阅】本周阅读摘选2026-02-16 → 2026-02-22

本周阅读摘选 2026-02-16 → 2026-02-22 目录技术技巧 Python & Google丨利用LLM从非结构化数文本中提取结构化数据字节跳动技术团队丨当 OpenClaw 内置 LanceDB：为个人 AI 智能体打造超强长期记忆 Memory模块解读 A complete guide to building skills for Claude ...

Posted by Cao Zihang on February 23, 2026

【阅】本周阅读摘选2026-02-09 → 2026-02-15

本周阅读摘选 2026-02-09 → 2026-02-15 目录学术相关 Analyzing consumer footprints on E-commerce platforms: a multichannel sequential search model with reference price AlphaOPT: formulating optimization programs with self-improving LLM experience l...

Posted by Cao Zihang on February 16, 2026