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

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
@@ -1,4 +1,4 @@
[[Tree-of-Thought (ToT, 사고 트리)]]
[[Tree-of-Thought (ToT, 사고 트리)|Tree-of-Thought (ToT, 사고 트리)]]
📌 Brief Summary
@@ -92,8 +92,8 @@ Tree-of-Thought(ToT)는 LLM이 문제를 선형 단계(Chain-of-Thought)가 아
🔗 Knowledge Connections
- **Related Topics:** [[Chain-of-Thought (CoT, 사고 사슬)]], [[ReAct (Reasoning + Acting)]], [[강화학습 (Reinforcement Learning)]], [[GRPO (Group Relative Policy Optimization)]], [[Multi-Hop Reasoning (다중 홉 추론)]], [[Self-Consistency (자기 일관성)]]
- **Projects/Contexts:** [[AI 추론 시스템]]
- **Related Topics:** [[Chain-of-Thought (CoT, 사고 사슬)|Chain-of-Thought (CoT, 사고 사슬)]], [[ReAct (Reasoning + Acting)|ReAct (Reasoning + Acting)]], [[강화학습 (Reinforcement Learning)|강화학습 (Reinforcement Learning)]], [[GRPO (Group Relative Policy Optimization)|GRPO (Group Relative Policy Optimization)]], [[Multi-Hop Reasoning (다중 홉 추론)|Multi-Hop Reasoning (다중 홉 추론)]], Self-Consistency (자기 일관성)
- **Projects/Contexts:** AI 추론 시스템
- **Contradictions/Notes:**
- ToT는 비용 대비 성능 트레이드오프가 극단적 → 실시간 서비스보다 오프라인 배치·연구용으로 적합.
- **신규 키워드**: `MCTS (몬테카를로 트리 탐색)`, `Self-Evaluation`, `Backtracking` → 탐색 큐 추가.