Skip to content

Framework & Architecture

框架設計、編排架構、scaffold、workflow engine、持久執行

131 papers Tool Use, Multi-Agent

Agent Evaluation

評測方法論、benchmark 設計、能力邊界測試、shadow evaluation

106 papers Agent Security, Coding Agent

Agent Security

prompt injection、對抗攻擊、guardrails、沙箱隔離、紅隊測試

46 papers Agent Evaluation, Deployment & Production

Agent Memory

記憶管理、context window、遺忘機制、episodic memory、長程任務記憶

32 papers RAG & Retrieval, Reasoning & Planning

Multi-Agent

多 Agent 協定、角色分工、MCP、A2A、通訊架構

31 papers Framework & Architecture, Agent Security

Deployment & Production

推理成本、延遲最佳化、可觀測性、企業落地、規模化

25 papers Agent Security, Agent Evaluation

Reasoning & Planning

chain-of-thought、planning、決策、搜尋策略、self-reflection

23 papers Agent Memory, Tool Use

Coding Agent

AI 程式碼生成、SWE-bench、自主修 bug、code review、IDE 整合

18 papers Agent Evaluation, Tool Use

RAG & Retrieval

retrieval-augmented generation、向量檢索、知識庫、document parsing

15 papers Agent Memory, Tool Use

Tool Use

function calling、API 呼叫最佳化、工具選擇、工具組合

5 papers Reasoning & Planning, Framework & Architecture