Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
54 lines
10 KiB
XML
54 lines
10 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 880 490" width="880" height="490" 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>
|
|
<style>text { font-family: "Noto Sans CJK KR", "Apple SD Gothic Neo", "Malgun Gothic", Arial, sans-serif !important; }</style>
|
|
|
|
<rect x="20" y="55" width="400" height="460" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
|
<text x="220" y="78" 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">도구 호출형 (Verifiers)</text>
|
|
<rect x="120" y="95" width="200" height="42" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="220.0" y="116.0" 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">Agent (LLM)</text>
|
|
<line x1="220" y1="137" x2="220" y2="168" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<rect x="60" y="170" width="320" height="80" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="220" y="192" 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">도구 실행 환경</text>
|
|
<rect x="75" y="200" width="290" height="48" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="85" y="219.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">run_python("def fib(n): ...")</text>
|
|
<text x="85" y="237.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">→ {"result": [1,1,2,3,5,8]}</text>
|
|
<line x1="220" y1="250" x2="220" y2="278" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<rect x="60" y="280" width="320" height="80" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="220" y="302" 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">실행 가능 검증기</text>
|
|
<rect x="75" y="312" width="290" height="48" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="85" y="331.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">assert fib(10) == 55 # PASS</text>
|
|
<text x="85" y="349.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">assert fib(0) == 0 # PASS</text>
|
|
<line x1="220" y1="360" x2="220" y2="390" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<rect x="100" y="392" width="240" height="40" rx="6" fill="#999999" stroke="#333333" stroke-width="2"/>
|
|
<text x="220" y="412" 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="#ffffff" text-anchor="middle" dominant-baseline="central" font-weight="bold">reward = 1.0 (모두 통과)</text>
|
|
<rect x="80" y="445" width="280" height="30" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="90" y="460" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">특징: 사람/LLM의 판정 불필요</text>
|
|
<rect x="460" y="55" width="400" height="460" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
|
<text x="660" y="78" 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">인간-컴퓨터 상호작용형 (τ-bench)</text>
|
|
<rect x="475" y="95" width="165" height="42" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="557.5" y="116.0" 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">사용자 시뮬레이터</text>
|
|
<rect x="680" y="95" width="165" height="42" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="762.5" y="116.0" 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">Agent (LLM)</text>
|
|
<line x1="640" y1="108" x2="678" y2="108" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<text x="660.0" y="148.0" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="middle" font-style="italic">"항공편에 문제가 있어요"</text>
|
|
<line x1="680" y1="128" x2="642" y2="128" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<line x1="762" y1="137" x2="762" y2="168" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<rect x="490" y="170" width="340" height="80" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="660" y="192" 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">도구 호출</text>
|
|
<rect x="505" y="200" width="310" height="48" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="515" y="219.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">lookup_booking("BK-98712")</text>
|
|
<text x="515" y="237.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="10" fill="#333333" text-anchor="start" dominant-baseline="central">→ {"status":"confirmed","flight":"UA123"}</text>
|
|
<line x1="660" y1="250" x2="660" y2="278" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<rect x="490" y="280" width="340" height="100" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="660" y="302" 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">이중 검증</text>
|
|
<rect x="505" y="312" width="310" height="66" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="515" y="331.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">① DB: booking.status == "cancelled"</text>
|
|
<text x="515" y="349.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">② 대화: "환불 $150" 포함</text>
|
|
<text x="515" y="367.0" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central"> "영업일 기준 3~5일 이내 입금" 포함</text>
|
|
<line x1="660" y1="380" x2="660" y2="406" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<rect x="520" y="408" width="280" height="40" rx="6" fill="#999999" stroke="#333333" stroke-width="2"/>
|
|
<text x="660" y="428" 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="#ffffff" text-anchor="middle" dominant-baseline="central" font-weight="bold">reward = 0/1 (둘 다 통과)</text>
|
|
<rect x="500" y="460" width="320" height="30" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="510" y="475" font-family="'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Noto Sans Mono CJK KR', 'D2Coding', 'Apple SD Gothic Neo', 'Malgun Gothic', 'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">특징: 단계적 정보 공개 + 상태 검증</text>
|
|
</svg>
|