AI 工程与智能体
从论文中的方法到产品中的取舍，理解模型、记忆、验证与日常工作流。
55 篇文章 · 5 个系列
选择系列
论文笔记 →
- 【论文笔记】019 Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
- 【论文笔记】020 Generative Agents - Interactive Simulacra of Human Behavior
- 【论文笔记】021 A-Mem - Agentic Memory for LLM Agents
- 【论文笔记】022 Beyond Static Summarization - Proactive Memory Extraction for LLM Agents
- 【论文笔记】023 HippoRAG - Neurobiologically Inspired Long-Term Memory for Large Language Models
- 【论文笔记】024 LongMemEval - Benchmarking Chat Assistants on Long-Term Interactive Memory
展开其余 21 篇
- 【论文笔记】025 Seeing, Listening, Remembering, and Reasoning - A Multimodal Agent with Long-Term Memory
- 【论文笔记】026 Mem0 - Building Production-Ready AI Agents with Scalable Long-Term Memory
- 【论文笔记】010 A Survey of Personalized Large Language Models - Progress and Future Directions
- 【论文笔记】011 A Survey on Personalized Alignment - The Missing Piece for Large Language Models in Real-World Applications
- 【论文笔记】012 Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona Prompting
- 【论文笔记】013 CharacterGPT - A Persona Reconstruction Framework for Role-Playing Agents
- 【论文笔记】014 Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
- 【论文笔记】015 From Persona to Personalization - A Survey on Role-Playing Language Agents
- 【论文笔记】016 LLM Generated Persona is a Promise with a Catch
- 【论文笔记】017 PersonaFeedback - A Large-scale Human-annotated Benchmark for Personalization
- 【论文笔记】018 PersonaLens - A Benchmark for Personalization Evaluation in Conversational AI Assistants
- 【论文笔记】009 Sparks of Artificial General Intelligence - Early experiments with GPT-4
- 【论文笔记】008 Generative Agents - Interactive Simulacra of Human Behavior
- 【论文笔记】007 A Vertical Federated Learning Method for Interpretable Scorecard and Its Application in Credit Scoring
- 【论文笔记】006 Advances and Open Problems in Federated Learning
- 【论文笔记】005 Frustratingly Easy Domain Adaptation
- 【论文笔记】004e Feedback Control of Real-Time Display Advertising 代码解析
- 【论文笔记】004 Feedback Control of Real-Time Display Advertising
- 【论文笔记】003 Auto-Keras - An Efficient Neural Architecture Search System
- 【论文笔记】002 Optimal RealTime Bidding for Display Advertising
- 【论文笔记】001 A TensorFlow-Based Production-Scale Machine Learning Platform
AI Talk →
- 【AI Talk】22 痛苦才是壁垒
- 【AI Talk】21 绕开 Loop 和知识图谱
- 【AI Talk】20 好的研发需要什么样的 Coding Agent
- 【AI Talk】19 公司与产品的活人感
- 【AI Talk】18 模型越大，模型越小
- 【AI Talk】17 概率、成本与确定性
展开其余 17 篇
- 【AI Talk】16 Contexts 和 Loop 对大部分人来说并不重要
- 【AI Talk】15 尽早开始构建验证流
- 【AI Talk】14 豆包值 68 还是 500
- 【AI Talk】13 置身 AI 内
- 【AI Talk】12 对 Agent 严肃的公司一定会做自己的模型
- 【AI Talk】11 Token 的工程汇率学
- 【AI Talk】10 Human in the loop 是 Agent 的点睛之笔
- 【AI Talk】09 融合 Skills、大模型和 Python 的 Harness 工程控制论实践
- 【AI Talk】08 Agent 带来的工程质量幻觉
- 【AI Talk】07 OpenClaw 和 Claude Code 怎么选
- 【AI Talk】06 决定最佳 AI 同步率的两个关键要素
- 【AI Talk】05 也谈 OpenClaw：日记即记忆
- 【AI Talk】04 看后视镜做不到第一名
- 【AI Talk】03 小土刀的AI猜想2026
- 【AI Talk】02 敢问 Agent 路在何方
- 【AI Talk】01 等待戈多的 Manus 们
- 【AI Talk】00 系列概览