The silent page awaits the waking dawn.
Category: 阅读 - 知行
Category
19
articles · from 2025
阅读
2026
12 entries
MAGRPO: Training LLMs That Truly Collaborate with Multi-Agent Reinforcement Learning
#Concept
Jun 25
From MDP to Dec-POMDP: Understanding the Differences Between Single-Agent and Multi-Agent Decision Models
#Concept
Jun 25
Do a truly in-depth research session with the STORM method
#Learning
Jun 23
How to Do Software Engineering in the Agent Era
Mar 11
别再迷信一个“万能大模型”了：用多专家 LLM 提升电商多语言搜索相关性
#arXiv
Feb 5
MixLM：让 LLM 排序又强又快的工程级方案
#arXiv
Feb 4
Agentic Context Engineering（ACE）：让大模型“越用越聪明”的上下文工程方法
#arXiv
Feb 3
用“流水线思维”重构 AI Agent：《Monadic Context Engineering》的大白话解读
#arXiv
Jan 27
AdaMARP：把「会演戏」和「会导戏」分开的多智能体角色扮演框架
#arXiv
Jan 21
DDIA 2-1 复制
#Learning
Jan 9
SimpleMem：给 LLM Agent 装上「会整理的终身记忆」——小白也能看懂的长期记忆框架
#arXiv
Jan 8
InfiAgent：让 AI Agent 像“做项目”一样工作（而不是把聊天记录堆到爆）
#arXiv
Jan 8
2025
7 entries
DDIA 1-5 编码与演化
#Learning
Dec 23
PAACE：面向计划感知的自动化智能体上下文工程框架
#arXiv
Dec 23
DDIA 1-4 存储与检索
#Learning
Dec 15
DDIA 1-3-2 图数据模型、事件溯源与 CQRS
#Learning
Dec 9
DDIA 1-3-1 关系模型与文档模型
#Learning
Dec 3
DDIA 1-2 定义非功能性需求
#Learning
Dec 1
DDIA 1-1 数据系统架构中的权衡：简单解析与思考
#Learning
Nov 26
Tags in this category
Back to top
#Learning
8
#arXiv
8
#Concept
2