bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_Blog/Agent Architecture.md
+2 -2
View File
@@ -6,7 +6,7 @@ tags: [auto-reinforced, agent-architecture, ai-agents, cognitive-architecture, m
last_reinforced: 2026-04-20
---
# [[Agent Architecture]]
# [[Agent Architecture|Agent Architecture]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "자율 주행하는 지능의 내부 구조: 단순히 답을 내는 모델을 넘어, 기억(Memory), 계획(Planning), 도구 활용(Tool Use) 기능을 유기적으로 결합하여 독립적으로 미션을 수행하는 에이전트의 뇌 설계."
@@ -31,6 +31,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: 에이전트의 자율 통제 불능 리스크를 방어하기 위해, 매 행동 단계마다 인간이 승인하거나 규칙을 검증하는 'Human-in-the-loop 에이전트 거버넌스' 정책이 산업 표준으로 채택됨.
## 🔗 지식 연결 (Graph)
- [[Ps-Reinforce]], Foundational Models, [[Workflow-Integrity]], [[Self-Correction Mechanisms]], [[Tool-Usage-Optimization]]
- [[Ps-Reinforce|Ps-Reinforce]], Foundational Models, [[Workflow-Integrity|Workflow-Integrity]], Self-Correction Mechanisms, [[Tool-Usage-Optimization|Tool-Usage-Optimization]]
- **Modern Tech/Tools**: LangChain, AutoGPT, BabyAGI, Microsoft AutoGen, LangGraph.
---