PathOnAI LogoPathOnAI

Our AI Agents Projects

Explore our current and past projects dedicated to advancing open-source development and AGI research.

Featured Projects

VisualTreeSearch
Use arrows to navigate

VisualTreeSearch

An intuitive interface for understanding web agent decision processes. Visualize and understand how web agents make decisions as they navigate complex tasks.

Learn More

Publications

Purple text indicates authors affiliated with PathOnAI.org.

  • VisualTreeSearch: Understanding Web Agent Test-time Scaling[Paper]
    Danqing Zhang, Yaoyao Qian, Shiying He, Yuanli Wang, Jingyi Ni, Junyu Cao
  • LiteMultiAgent: A Multi-Agent Framework for LLM-Based Applications[work in progress]
    Danqing Zhang, Jingyi Ni,
    (Paper title and author list may be modified)
  • Web Agent Evaluation Metrics[work in progress]
    Shiying He, Yaoyao Qian, Danqing Zhang, Yuanli Wang
    (Paper title and author list may be modified)
  • Tutorial on Landing Generative AI in Industrial Social and E-commerce Recsys[Paper]
    Da Xu, Danqing Zhang, Chuanwei Ruan, Lingling Zheng, Bo Yang, Guangyu Yang, Shuyuan Xu and Haixun Wang
    WWW'25: The Web Conference Tutorial
  • LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications[Paper]
    Danqing Zhang, Balaji Rama, Jingyi Ni, Shiying He, Fu Zhao, Kunyu Chen, Arnold Chen, Junyu Cao
    NAACL'25: 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics -- System Demonstration Track
  • Tutorial on Landing Generative AI in Industrial Social and E-commerce Recsys[Paper]
    Da Xu, Danqing Zhang, Lingling Zheng, Bo Yang, Guangyu Yang, Shuyuan Xu, Cindy Liang
    CIKM'24: The Conference on Information and Knowledge Management (CIKM) Tutorial
  • Survey for Landing Generative AI in Social and E-commerce Recsys -- the Industry Perspectives[Paper]
    Da Xu, Danqing Zhang, Guangyu Yang, Bo Yang, Shuyuan Xu, Lingling Zheng, Cindy Liang
    KDD GenAIRecP'25: Knowledge Discovery and Data Mining (KDD) Generative AI for Recommender Systems and Personalization Workshop, 2024

Research Philosophy

  • 🔍Make user interfaces more intuitive for understanding and interpreting AI decision-making processes
  • 🧮Formulate real-world applications into mathematical models to find optimal solutions
  • 🔄Bridge the gap between academic research and production applications by raising the bar on code quality
  • 📊Conduct detailed ablation studies to examine when and why approaches work better

Current Projects

  • 🌐Lite Web Agent Tree Search[GitHub]
    Enhancing web agents with tree search algorithms for improved decision-making and task completion.
  • 🧠Generative Agent Based Simulation
    Creating realistic multi-agent simulations powered by LLMs to model complex social interactions and emergent behaviors in virtual environments.

Past Projects

  • 👥LiteMultiAgent[GitHub]
    A library for LLM-based multi-agent applications.
  • 🌍LiteWebAgent[GitHub]
    A library for LLM-based web-agent applications.
  • 🤖LiteGUIAgent[GitHub]
    A library for VLM-based computer control agent. To be released.
  • 📚Awesome AI Agents[GitHub]
    Collection of Materials on AI Agents.
  • 💻Natural Language Terminal[GitHub]
    Takes a natural language command and directly calls into the OS.
  • 🧠ARC AGI Experiments[GitHub]
    Exploring advanced reasoning capabilities in artificial intelligence systems.
  • 📚Awesome ARC AGI[GitHub]
    Collection of resources on advanced reasoning and cognitive architectures for AGI.
  • 🎮3D Embodied Agent[GitHub]
    Developing embodied AI agents for Roblox games.
  • 📚Awesome 3D Embodied AI[GitHub]
    Curated list of resources for 3D embodied AI research and development.