Agentic Scientific Workflows: From Search to Traceable Decisions
A working model for scientific agents that retrieve evidence, plan the next step, preserve uncertainty, and leave a decision trail.
关于 AI 智能体、科学工作流自动化、RAG、evaluation,以及电池材料研究与应用 AI 系统之间连接的工作笔记。
A working model for scientific agents that retrieve evidence, plan the next step, preserve uncertainty, and leave a decision trail.
Why a personal technical site can be more useful when the homepage becomes a small, cited, public-safe agent.
RAG systems for technical work should be judged by retrieval quality, citation faithfulness, and decision usefulness, not only fluent answers.
新文章是 src/content/blog 下的 Markdown 文件。
用脚本生成带日期和 frontmatter 的草稿,再编辑正文并提交。
npm run new:post -- --title "My AI agent note"