Skip to content
@DataArcTech

DataArcTech

Welcome to DataArc Tech Inc.

⚡DataArcTech⚡

👉 Data-Driven, Intelligently Synthesized

🔥 We specialize in intelligent synthetic data generation and knowledge-augmented LLM reasoning technologies.

🌟 With a focus on context graphs and multi-agent systems, we build more efficient and trustworthy next-generation data and model infrastructure.

🚀 Through open-source projects and in-depth research, we explore the full technical cycle from data synthesis and continual pre-training to model evaluation.

👋 Join us in contributing high-quality algorithms, data, and insights to the open-source community.

         

Popular repositories Loading

  1. DataArc-SynData-Toolkit DataArc-SynData-Toolkit Public

    Synthetic Data Generation Platform By DataArcTech

    Python 684 12

  2. ToG ToG Public

    This is the official github repo of Think-on-Graph (ICLR 2024). If you are interested in our work or willing to join our research team in Shenzhen, please feel free to contact us by email (xuchengj…

    Python 615 68

  3. LLM-as-a-Judge LLM-as-a-Judge Public

    167 5

  4. SQL-R1 SQL-R1 Public

    [NeurIPS'25] Official Repository for the Paper "SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning"

    Python 119 16

  5. ToG-2 ToG-2 Public

    Python 101 17

  6. ChartMoE ChartMoE Public

    [ICLR2025 Oral] ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding

    Jupyter Notebook 95 8

Repositories

Showing 10 of 28 repositories
  • RAG-ARC Public

    A modular, high-performance Retrieval-Augmented Generation framework with multi-path retrieval, graph extraction, and fusion ranking

    DataArcTech/RAG-ARC’s past year of commit activity
    Python 23 MIT 9 1 2 Updated Jan 9, 2026
  • .github Public
    DataArcTech/.github’s past year of commit activity
    0 0 0 0 Updated Jan 9, 2026
  • DataArc-SynData-Toolkit Public

    Synthetic Data Generation Platform By DataArcTech

    DataArcTech/DataArc-SynData-Toolkit’s past year of commit activity
    Python 684 12 1 0 Updated Jan 9, 2026
  • Awesome-LLMs-for-Mathematical-Modeling Public

    🥇 A curated list of awesome Large Language Models/Agents for Mathematical Modeling tasks, including papers,models,datasets and codebases. 专门用于数学建模任务的大模型/Agent。

    DataArcTech/Awesome-LLMs-for-Mathematical-Modeling’s past year of commit activity
    0 Apache-2.0 0 0 0 Updated Jan 8, 2026
  • DataArcTech/AIPracticePartner’s past year of commit activity
    Go 0 0 0 0 Updated Jan 7, 2026
  • ToG-3 Public

    Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

    DataArcTech/ToG-3’s past year of commit activity
    Python 66 MIT 8 5 0 Updated Dec 5, 2025
  • SQL-R1 Public

    [NeurIPS'25] Official Repository for the Paper "SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning"

    DataArcTech/SQL-R1’s past year of commit activity
    Python 119 Apache-2.0 16 0 0 Updated Nov 20, 2025
  • GraphSearch Public

    GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

    DataArcTech/GraphSearch’s past year of commit activity
    Python 80 Apache-2.0 6 0 0 Updated Nov 3, 2025
  • DataArcTech/LLM-as-a-Judge’s past year of commit activity
    167 5 3 0 Updated Oct 12, 2025
  • JudgeAgent Public

    This is the source code of the paper "JudgeAgent: Dynamically Evaluate LLMs with Agent-as-Interviewer".

    DataArcTech/JudgeAgent’s past year of commit activity
    Python 3 0 0 0 Updated Sep 25, 2025