liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
Build latest book artifacts / build (push) Canceled after 0s
Details
dependency resolution / resolve (3.11) (push) Canceled after 0s
Details
dependency resolution / resolve (3.13) (push) Canceled after 0s
Details
deploy-pages / build (push) Canceled after 0s
Details
deploy-pages / deploy (push) Canceled after 0s
Details
i18n consistency check / check (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
Details
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
Details
web-search-agent tests / test (push) Canceled after 0s
Details
web-search-agent tests / agentbook (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
liqiang
2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
book-ko/images/fig8-11.svg
+25
View File
@@ -0,0 +1,25 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 340" width="780" height="340" style="background:#ffffff">
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
<rect x="40" y="65" width="300" height="130" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
<text x="190" y="88" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">1단계: SFT로 형식 고정</text>
<text x="190" y="115" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">목표: 파싱 가능한 출력(JSON/도구 호출)</text>
<text x="190" y="137" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">데이터: 고품질 시연 수천 건</text>
<text x="190" y="159" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">중단 조건: 형식 안정, 기본 역량 확보</text>
<text x="190" y="181" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">⚠ 과도한 학습 → 모델이 학습 분포로 붕괴</text>
<line x1="342" y1="130" x2="398" y2="130" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
<text x="370" y="115" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">형식</text>
<text x="370" y="135" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">안정</text>
<rect x="400" y="65" width="340" height="130" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
<text x="570" y="88" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">2단계: RL로 정책 형성</text>
<text x="570" y="115" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">목표: 작업 보상 최대화(정확도/성공률)</text>
<text x="570" y="137" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">전제: 출력 형식 안정 → 보상 계산 가능</text>
<text x="570" y="159" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">돌파: SFT 시연을 뛰어넘는 새 전략 발견</text>
<text x="570" y="181" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">✓ 형식 안정 + 전략 일반화 = 배포 준비 완료</text>
<rect x="40" y="220" width="700" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
<text x="390" y="238" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">왜 SFT를 건너뛰고 곧바로 RL을 할 수 없는가?</text>
<text x="390" y="262" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">기반 모델 출력이 비구조적 → JSON 파싱 불가 → 보상 함수가 NaN 반환 → 그래디언트 0 → 학습 완전 실패</text>
<text x="390" y="310" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">SFT는 분포를 암기 → RL은 전략을 일반화</text>
<text x="390" y="338" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">SFT: max Σ log P(y|x)(학습 분포 적합) RL: max E[R(τ)](작업 목표 최적화)</text>
<text x="390" y="362" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">&quot;시연을 아무리 늘려도 새 상황에서 성능이 나쁘다&quot;면 → RL로 전환할 임계점</text>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 6.2 KiB