liqiang
b119135836
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
68 lines
11 KiB
XML
68 lines
11 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 15 880 545" width="880" height="545" 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="20" y="70" width="220" height="230" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
|
<text x="130" y="93" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">User Simulator (LLM)</text>
|
|
<line x1="30" y1="105" x2="230" y2="105" stroke="#999999" stroke-width="2"/>
|
|
<text x="30" y="115" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Known Information:</text>
|
|
<text x="35" y="133" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">Name: Sarah Johnson</text>
|
|
<text x="35" y="151" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">Booking: BK-98712</text>
|
|
<text x="30" y="177" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Task Instruction:</text>
|
|
<text x="35" y="195" font-family="'Courier New', Courier, monospace" font-size="7" fill="#333333" text-anchor="start" dominant-baseline="central">"There seems to be a problem with the flight"</text>
|
|
<text x="35" y="213" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">→ Gradually reveal details</text>
|
|
<text x="35" y="231" font-family="'Courier New', Courier, monospace" font-size="7" fill="#333333" text-anchor="start" dominant-baseline="central">→ Do not proactively provide the booking number</text>
|
|
<rect x="300" y="70" width="260" height="230" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
|
<text x="430" y="93" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Agent (To Be Evaluated)</text>
|
|
<line x1="310" y1="105" x2="550" y2="105" stroke="#999999" stroke-width="2"/>
|
|
<rect x="315" y="115" width="230" height="40" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="430" y="135" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">LLM Reasoning + Strategy Selection</text>
|
|
<text x="320" y="175" font-family="'Courier New', Courier, monospace" font-size="11.5" fill="#333333" text-anchor="start" dominant-baseline="central">① May I have your booking number?</text>
|
|
<text x="320" y="197" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">② lookup_booking(BK-98712)</text>
|
|
<text x="320" y="219" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">③ Flight UA123 has been canceled</text>
|
|
<text x="320" y="241" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">④ cancel_booking(BK-98712)</text>
|
|
<text x="320" y="263" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">⑤ Refund $150, 3-5 business days</text>
|
|
<rect x="620" y="70" width="240" height="230" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
|
<text x="740" y="93" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Tools + Database</text>
|
|
<line x1="630" y1="105" x2="850" y2="105" stroke="#999999" stroke-width="2"/>
|
|
<text x="635" y="120" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">lookup_booking</text>
|
|
<text x="780" y="120" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Query booking details</text>
|
|
<text x="635" y="142" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">modify_booking</text>
|
|
<text x="780" y="142" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Modify booking status</text>
|
|
<text x="635" y="164" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">cancel_booking</text>
|
|
<text x="780" y="164" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Cancel and refund</text>
|
|
<text x="635" y="186" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">search_flights</text>
|
|
<text x="780" y="186" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Search for alternative flights</text>
|
|
<text x="635" y="208" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">send_notification</text>
|
|
<text x="780" y="208" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">Send confirmation notification</text>
|
|
<rect x="630" y="240" width="220" height="45" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
|
<text x="640" y="255" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">DB State:</text>
|
|
<text x="640" y="273" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">bookings, users, flights</text>
|
|
<line x1="240" y1="150" x2="298" y2="150" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<text x="269.0" y="140.0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle">Dialogue</text>
|
|
<line x1="300" y1="180" x2="242" y2="180" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<line x1="560" y1="155" x2="618" y2="155" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<text x="589.0" y="145.0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle">Tool Call</text>
|
|
<line x1="618" y1="185" x2="560" y2="185" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
|
<path d="M 130,68 Q 435,30 740,68" fill="none" stroke="#666666" stroke-width="2" stroke-dasharray="6,3" marker-end="url(#ah-light)"/>
|
|
<text x="435" y="26" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="bold">Dual-control environment: User simulator can also directly operate the shared environment (tools + database)</text>
|
|
<line x1="20" y1="320" x2="860" y2="320" stroke="#999999" stroke-width="2" stroke-dasharray="8,4"/>
|
|
<text x="440.0" y="345" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">After task completion: Multi-layer verification</text>
|
|
<rect x="40" y="365" width="260" height="170" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="170" y="388" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">DB status check</text>
|
|
<line x1="50" y1="400" x2="290" y2="400" stroke="#999999" stroke-width="2"/>
|
|
<text x="55" y="420" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">booking.status == 'cancelled'</text>
|
|
<text x="55" y="444" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">refund_record EXISTS</text>
|
|
<text x="55" y="468" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">refund.amount == 150.00</text>
|
|
<rect x="320" y="365" width="260" height="170" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="450" y="388" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Dialogue content verification</text>
|
|
<line x1="330" y1="400" x2="570" y2="400" stroke="#999999" stroke-width="2"/>
|
|
<text x="335" y="420" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">Contains 'refund' + amount</text>
|
|
<text x="335" y="444" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">Contains 'arrival time'</text>
|
|
<text x="335" y="468" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">No false information present</text>
|
|
<rect x="600" y="365" width="260" height="170" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="730" y="388" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Process compliance check</text>
|
|
<line x1="610" y1="400" x2="850" y2="400" stroke="#999999" stroke-width="2"/>
|
|
<text x="615" y="420" font-family="'Courier New', Courier, monospace" font-size="9" fill="#333333" text-anchor="start" dominant-baseline="central">Obtain user confirmation before modification</text>
|
|
<text x="615" y="444" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">No unauthorized operation</text>
|
|
<text x="615" y="468" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">No excessive transfer to human agent</text>
|
|
</svg> |
