Views
No views yet
search / scrape / python tool implementations, fixed tool contract, replayable context management, and benchmark evaluation workflow; these capabilities are supplied by the surrounding harness rather than by the checkpoint alone.
| Benchmark | XYZ-Aquila-mini | Agents-A1 | Nex-N2-mini | apodex-mini | MiroThinker 1.7 mini |
|---|---|---|---|---|---|
| BrowseComp | 78.8 | 75.5 | 74.1 | 71.5 | 67.9 |
| BrowseComp-ZH | 82.9 | -- | 79.6† | 80.6 | -- |
| DeepSearchQA | 89.5 | -- | 87.2† | 82.2 | -- |
| GAIA | 97.1 | 96.0 | -- | -- | 80.3 |
| LiveBrowseComp | 48.7 | 29.6† | 41.4† | 32.8† | 34.9† |
| HLE | 51.1 | 47.6 | 37.1† | 46.8 | 36.4 |
| WideSearch | 80.8 | -- | 62.0 | -- | 73.3† |
| Benchmark | XYZ-Aquila-pro | Nex-N2-Pro | MiroThinker 1.7 | apodex-1.0 |
|---|---|---|---|---|
| BrowseComp | 84.8 | 83.7† | 74.0 | 75.5 |
| BrowseComp-ZH | 85.1 | 79.6† | 75.3 | 82.6 |
| DeepSearchQA | 92.5 | 92.3† | -- | 84.6 |
| LiveBrowseComp | 53.7 | 50.4† | 34.1† | -- |
| HLE | 53.3 | 50.0† | 42.9 | 49.0 |
| WideSearch | 81.2 | 75.6 | -- | -- |
| Benchmark | XYZ-Aquila-pro | apodex-h1 | DeepSeek-V4- Pro-Max | Kimi-K2.6 | Claude Opus 4.7 | GPT-5.5 xhigh |
|---|---|---|---|---|---|---|
| BrowseComp | 84.8 | 90.3 | 83.4 | 83.2 | 79.3 | 84.4 |
| BrowseComp-ZH | 85.1 | 84.1 | -- | -- | -- | -- |
| DeepSearchQA | 92.5 | 94.4 | -- | 92.5 | 89.1 | -- |
| LiveBrowseComp | 53.7 | -- | 38.3 | 31.7 | -- | -- |
| HLE | 53.3 | 60.8 | -- | 55.5 | 54.7 | 52.2 |
| WideSearch | 81.2 | -- | -- | 80.8 | -- | -- |
-- indicates an unreported result within an otherwise populated row. † marks results reproduced under the common evaluation setup; other baseline values come from public reports or benchmark submissions. See the technical report for full provenance and analysis.sglang>=0.5.14 for XYZ-Aquila-pro.uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python&egg=sglang[all]'1MODEL_PATH=XYZAILab/XYZ-Aquila-pro
2SERVED_MODEL=XYZ-Aquila-pro
3
4python -m sglang.launch_server \
5 --model-path "${MODEL_PATH}" \
6 --served-model-name "${SERVED_MODEL}" \
7 --port 8000 \
8 --tp-size 8 \
9 --mem-fraction-static 0.8 \
10 --context-length 262144 \
11 --reasoning-parser qwen3 \
12 --tool-call-parser qwen3_coder1import requests
2
3BASE_URL = "http://localhost:8000/v1"
4MODEL_NAME = "XYZ-Aquila-pro"
5
6SYSTEM_PROMPT = r"""You are a task-solving research agent with access to native structured tools.
7Use the tools step-by-step to answer the user's question accurately and completely.
8Today is: 2026-06-27
9
10# Tool-Use Rules
11
12- Use the function-calling interface to invoke tools. Do not write tool calls as plain text.
13- Call at most ONE tool per assistant turn. The next message will contain that tool's result; use it to decide your next step.
14- Only use tools declared in the provided tools schema.
15- Use web_search to discover relevant sources, verify facts, or find promising URLs.
16- Use scrape_and_extract_info to read a specific URL or extract focused facts from a page.
17- Prefer focused searches and focused extraction requests. Avoid repeating the same query or URL unless the previous result was unusable.
18- For source-grounded questions, do not rely only on search snippets when a page needs to be inspected.
19
20# Answering
21
22- When you have sufficient evidence, stop calling tools and provide the final answer wrapped in \boxed{}.
23- Follow the user's requested output format exactly.
24- Keep the boxed answer concise: a number, short phrase, or comma-separated list when appropriate.
25- Do not output a final prose response without \boxed{}.
26"""
27
28USER_PROMPT = r"""In the mythological literature of a certain northern European region, the parental figure of a specified character was joined in a legal and social union with a ruler whose title was derived from a specific tribal designation. The name of that tribe was also adopted as the identifier for a historical Continental kingdom, whose final independent sovereign fell in armed conflict against a nomadic steppe confederation in the latter half of the 5th century. The character in question administered a prepared liquid to a male subject who had, in the narrative, taken possession of a hoard of precious metal and crafted objects. The hoard's origin was a confrontation between a male figure and a winged, venomous creature that had once been a male member of a specific lineage. The administration of the liquid led to the subject developing an altered perception of a prior commitment of matrimony. The later consequence, directly flowing from this event, was the coerced marriage of the subject's sister to the leader of the aforementioned nomadic confederation. Provide the name recorded for the character who prepared and administered the liquid.
29Follow the request's format instructions strictly and wrap the final answer in \boxed{}."""
30
31messages = [
32 {"role": "system", "content": SYSTEM_PROMPT},
33 {"role": "user", "content": USER_PROMPT},
34]
35
36tools = [
37 {
38 "type": "function",
39 "function": {
40 "name": "web_search",
41 "description": "Search the web using Google and return relevant results. Use this tool to find up-to-date information, verify facts, or discover URLs for further investigation.\n\nReturns structured search results including organic results, knowledge graph, and related questions.",
42 "parameters": {
43 "type": "object",
44 "properties": {
45 "query": {
46 "type": "string",
47 "description": "The search query string.",
48 },
49 "num": {
50 "type": "integer",
51 "description": "Number of results to return (default: 10, max: 100).",
52 "default": 10,
53 },
54 "hl": {
55 "type": "string",
56 "description": "Language code for results, e.g., 'en', 'zh', (ISO 639-1, default: 'en').",
57 "default": "en",
58 },
59 "gl": {
60 "type": "string",
61 "description": "Country code for localised results, e.g., 'us', 'gb', (ISO 3166-1 alpha-2, default: 'us').",
62 "default": "us",
63 },
64 },
65 "required": ["query"],
66 },
67 },
68 },
69 {
70 "type": "function",
71 "function": {
72 "name": "scrape_and_extract_info",
73 "description": "Fetch and read the contents of a web page, PDF, or other online document. Returns the page content as clean text. When 'info_to_extract' is provided, uses an LLM to extract only the relevant information from the page.\n\nUse this tool to read web pages found via web_search, examine documents, or access any URL-addressable content.",
74 "parameters": {
75 "type": "object",
76 "properties": {
77 "url": {
78 "type": "string",
79 "description": "The URL to scrape (web page, PDF, code file, etc.).",
80 },
81 "info_to_extract": {
82 "type": "string",
83 "description": "What specific information to extract from the page. If provided, returns a focused extraction instead of the full page content. If omitted, returns the full page content.",
84 },
85 },
86 "required": ["url"],
87 },
88 },
89 },
90 {
91 "type": "function",
92 "function": {
93 "name": "run_python_code",
94 "description": "Execute a self-contained snippet of Python code in a fresh, isolated sandbox and return its output.\n\nEach call runs in a brand-new sandbox with no memory of previous calls: include every import and define every variable you need inside `code`, and `print(...)` anything you want to read back. Use it for calculations, symbolic math (sympy), numeric work (numpy/scipy), data processing, and verifying intermediate results.\n\nArgs:\n code: The complete Python source to execute.\n\nReturns:\n The captured execution result (stdout, returned values, and any error/traceback).",
95 "parameters": {
96 "type": "object",
97 "properties": {
98 "code": {
99 "type": "string",
100 "description": "Self-contained Python code to execute. Print any value you want returned.",
101 },
102 },
103 "required": ["code"],
104 },
105 },
106 },
107]
108
109payload = {
110 "model": MODEL_NAME,
111 "messages": messages,
112 "tools": tools,
113 "temperature": 1.0,
114 "top_p": 0.95,
115 "repetition_penalty": 1.05,
116 "max_tokens": 32768,
117 "chat_template_kwargs": {
118 "enable_thinking": True,
119 "preserve_thinking": True,
120 },
121}
122
123response = requests.post(f"{BASE_URL}/chat/completions", json=payload, timeout=1800)
124response.raise_for_status()
125result = response.json()1temperature: 1.0
2top_p: 0.95
3repetition_penalty: 1.05
4max_tokens: 32768
5chat_template_kwargs:
6 enable_thinking: true
7 preserve_thinking: true1@techreport{xyz_aquila_2026,
2 title = {AI4AI at Scale: A Full-Pipeline System for Enhancing LLM Agentic Capabilities},
3 author = {{XYZ Agentic Team}},
4 institution = {XYZ AI Lab},
5 year = {2026},
6 url = {https://xyz-lab.ai/blogs/ai4ai-at-scale/assets/bounded-exploration-ai4ai-system-optimization.pdf}
7}