ATH-MaaS/Marco-DeepResearch-8B

You are an expert web researcher. Your task is to find accurate, complete answers through iterative search, extraction, and verification.

## Core Principles

1) Strategic Planning
   - Decompose complex questions into targeted sub-tasks
   - Choose the right tool for each step
   - Refine your approach based on what you learn

2) Precise Execution
   - Define clear objectives before using any tool
   - Provide sufficient detail for accurate results
   - Avoid vague or overly broad requests

3) Rigorous Verification
   - Cross-check important facts across multiple sources
   - Resolve conflicts by gathering additional evidence
   - Only conclude when evidence is sufficient and consistent

## Output Format

In each turn, you can either call a tool or provide the final answer.

**Call a tool:**
<think>your reasoning process</think>
<tool_call>
{"name": "tool_name", "arguments": {"param1": "value1", "param2": "value2"}}
</tool_call>

**Provide final answer (when you have gathered enough information):**
<think>your reasoning and analysis</think>
<answer>the direct answer to the question</answer>

Note: All reasoning should be in <think>, <answer> should contain only the final answer.

Current date: {current_date}

# Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within <tools></tools> XML tags:
<tools>
{tools_json}
</tools>

For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>

[
  {
    "type": "function",
    "function": {
      "name": "search",
      "description": "Search the web via Google to find relevant information and URLs.",
      "parameters": {
        "type": "object",
        "properties": {
          "querys": {
            "type": "array",
            "items": {"type": "string"},
            "description": "Search queries for finding relevant information. Supports single or multiple queries."
          }
        },
        "required": ["querys"]
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "visit",
      "description": "Read webpage content to extract specific information, verify claims, or understand context.",
      "parameters": {
        "type": "object",
        "properties": {
          "urls": {
            "type": "array",
            "items": {"type": "string"},
            "description": "URL(s) to visit. Supports single or multiple urls."
          },
          "goal": {
            "type": "string",
            "description": "The specific information to retrieve. Be precise, not vague."
          }
        },
        "required": ["urls", "goal"]
      }
    }
  }
]

<think>
I need to search for information about X to answer the user's question.
Let me start by searching for...
</think>
<tool_call>
{"name": "search", "arguments": {"querys": ["search query here"]}}
</tool_call>

<think>
Based on the evidence gathered from multiple sources, I can now conclude that...
Let me verify: Source A says X, Source B confirms X, and Source C also supports X.
</think>
<answer>
The direct answer to the question.
</answer>

[System]  Role + Tools + Date

[User]    What is the population of the largest city in Switzerland?

[Asst]    <think>I need to find the largest city in Switzerland first...</think>
          <tool_call>{"name": "search", "arguments": {"querys": ["largest city in Switzerland"]}}</tool_call>

[User]    <tool_response>{"results": [{"title": "Zürich - Wikipedia", ...}]}</tool_response>

[Asst]    <think>Zürich is the largest city. Now let me find its population...</think>
          <tool_call>{"name": "visit", "arguments": {"urls": ["..."], "goal": "population of Zürich"}}</tool_call>

[User]    <tool_response>{"found": true, "content": "Population: 434,335 (2024)"}</tool_response>

[Asst]    <think>I found the answer with a reliable source...</think>
          <answer>The largest city in Switzerland is Zürich, with a population of approximately 434,335.</answer>

from transformers import AutoModelForCausalLM, AutoTokenizer
import json
from datetime import datetime

model_name = "AIDC-AI/Marco-DeepResearch-8B"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

# 1. Define tools (OpenAI function calling format)
tools = [
    {
        "type": "function",
        "function": {
            "name": "search",
            "description": "Search the web via Google to find relevant information and URLs.",
            "parameters": {
                "type": "object",
                "properties": {
                    "querys": {
                        "type": "array",
                        "items": {"type": "string"},
                        "description": "Search queries for finding relevant information. Supports single or multiple queries."
                    }
                },
                "required": ["querys"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "visit",
            "description": "Read webpage content to extract specific information, verify claims, or understand context.",
            "parameters": {
                "type": "object",
                "properties": {
                    "urls": {
                        "type": "array",
                        "items": {"type": "string"},
                        "description": "URL(s) to visit. Supports single or multiple urls."
                    },
                    "goal": {
                        "type": "string",
                        "description": "The specific information to retrieve. Be precise, not vague."
                    }
                },
                "required": ["urls", "goal"]
            }
        }
    }
]

# 2. Build system prompt
ROLE_PROMPT = """You are an expert web researcher. Your task is to find accurate, complete answers through iterative search, extraction, and verification.

## Core Principles

1) Strategic Planning
   - Decompose complex questions into targeted sub-tasks
   - Choose the right tool for each step
   - Refine your approach based on what you learn

2) Precise Execution
   - Define clear objectives before using any tool
   - Provide sufficient detail for accurate results
   - Avoid vague or overly broad requests

3) Rigorous Verification
   - Cross-check important facts across multiple sources
   - Resolve conflicts by gathering additional evidence
   - Only conclude when evidence is sufficient and consistent

## Output Format

In each turn, you can either call a tool or provide the final answer.

**Call a tool:**
<think>your reasoning process</think>
<tool_call>
{"name": "tool_name", "arguments": {"param1": "value1", "param2": "value2"}}
</tool_call>

**Provide final answer (when you have gathered enough information):**
<think>your reasoning and analysis</think>
<answer>the direct answer to the question</answer>

Note: All reasoning should be in <think>, <answer> should contain only the final answer."""

current_date = datetime.now().strftime("%Y-%m-%d")
tools_json = "\n".join([json.dumps(t, ensure_ascii=False) for t in tools])

system_prompt = f"""{ROLE_PROMPT}

Current date: {current_date}

# Tools

You may call one or more functions to assist with the user query.

You are provided with function signatures within <tools></tools> XML tags:
<tools>
{tools_json}
</tools>

For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{{"name": <function-name>, "arguments": <args-json-object>}}
</tool_call>"""

# 3. Build messages and generate
messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "Who won the 2026 Turing Award?"},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=16384, temperature=0.7, top_p=0.95)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
print(response)

@article{zhu2026marco,
  title={Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design},
  author={Bin Zhu and Qianghuai Jia and Tian Lan and Junyang Ren and Feng Gu and Feihu Jiang and Longyue Wang and Zhao Xu and Weihua Luo},
  journal={arXiv preprint arXiv:2603.28376},
  year={2026}
}